© 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. 26834
    Prev
    Next
    INDEX
    Explanations

    natural

    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
     Deserialize
    -0.07
    部署
    -0.07
    硁
    -0.07
    otive
    -0.07
     SetProperty
    -0.07
     plain
    -0.07
     Thinking
    -0.07
     пс
    -0.06
    iguiente
    -0.06
    .Raw
    -0.06
    POSITIVE LOGITS
    が高い
    0.07
    ews
    0.07
    *",
    0.07
     PROCESS
    0.07
     R
    0.07
    뜬
    0.07
    荮
    0.06
    饱
    0.06
     {↵
    0.06
    можем
    0.06
    Activations Density 0.008%

    No Known Activations