© 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. 19-RESID-POST-AA
    11. 70940
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    展现了
    -0.08
    mando
    -0.07
    在意
    -0.07
    留住
    -0.07
    inski
    -0.07
    铈
    -0.07
    .intro
    -0.07
    战组合
    -0.07
    uve
    -0.07
    ركز
    -0.07
    POSITIVE LOGITS
     Liquid
    0.10
    濒临
    0.07
    ediator
    0.07
     Huffington
    0.07
    떴
    0.07
    条款
    0.07
    降价
    0.06
    機關
    0.06
    开发商
    0.06
    .setEditable
    0.06
    Activations Density 0.000%

    No Known Activations