© 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 EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 17927
    Prev
    Next
    INDEX
    Explanations

    from

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    قبال
    -0.07
     reefs
    -0.07
    toInt
    -0.07
     SQLException
    -0.07
    "]=
    -0.06
    リー
    -0.06
    שימוש
    -0.06
    还
    -0.06
    らせ
    -0.06
    薪酬
    -0.06
    POSITIVE LOGITS
    (phase
    0.07
    \Framework
    0.07
     powder
    0.07
     wildcard
    0.07
     british
    0.06
    微观
    0.06
    spinner
    0.06
    IPHER
    0.06
     Origins
    0.06
     uplift
    0.06
    Activations Density 0.324%

    No Known Activations