© 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. 7-RESID-POST-AA
    11. 81660
    Prev
    Next
    INDEX
    Explanations

    rew

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     loads
    -0.09
    Permissions
    -0.07
    Rose
    -0.07
    testing
    -0.07
     energy
    -0.07
    AllowAnonymous
    -0.07
     favor
    -0.07
    osas
    -0.07
    圣
    -0.07
    𝓉
    -0.07
    POSITIVE LOGITS
    .slf
    0.07
     כמו
    0.07
     الفندق
    0.07
     seja
    0.07
    时隔
    0.07
     inability
    0.07
    吃得
    0.07
    틈
    0.07
    بيعي
    0.07
    在此之前
    0.07
    Activations Density 0.004%

    No Known Activations