Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25762
    Prev
    Next
    INDEX
    Explanations

    system files/code

    np_max-act · gemini-2.0-flash
    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
    inda
    -0.07
     fingert
    -0.07
    ivan
    -0.07
    찟
    -0.06
     분
    -0.06
     outlook
    -0.06
    üstü
    -0.06
    abama
    -0.06
    usto
    -0.06
     Grat
    -0.06
    POSITIVE LOGITS
     Barnett
    0.07
    (!_
    0.07
     replicate
    0.07
     mile
    0.07
    accountId
    0.07
    pile
    0.07
    成名
    0.07
    lander
    0.07
    '<
    0.07
    不来
    0.06
    Activations Density 0.026%

    No Known Activations