© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 3138
    Prev
    Next
    INDEX
    Explanations

    advice and suggestions

    np_max-act · gemini-2.0-flash

    spots user requests to draft or write a message (email/letter/quote/script) — i.e., prompts asking the assistant to compose text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leadership
    -0.07
     Bá
    -0.06
     Bald
    -0.06
    דל
    -0.06
    .server
    -0.06
     lets
    -0.06
     absolutely
    -0.06
     מיד
    -0.06
    爱尔
    -0.06
     strategic
    -0.06
    POSITIVE LOGITS
    aced
    0.08
    olum
    0.07
    ▬
    0.07
     <*>
    0.07
    €™
    0.07
    Not
    0.07
    jsonwebtoken
    0.07
    ODB
    0.07
    paragus
    0.06
    cross
    0.06
    Activations Density 0.318%

    No Known Activations