© 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. 29951
    Prev
    Next
    INDEX
    Explanations

    github repositories

    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
    셌
    -0.07
    esters
    -0.07
    ej
    -0.06
    DEV
    -0.06
    трат
    -0.06
    返回
    -0.06
     Watts
    -0.06
    CAC
    -0.06
     sensitivity
    -0.06
     CREATE
    -0.06
    POSITIVE LOGITS
    _Link
    0.08
    散布
    0.07
     mosques
    0.07
    𝖎
    0.07
    .menu
    0.07
    完整的
    0.07
    国会
    0.07
    .enumer
    0.07
    //----------------------------------------------------------------------------↵
    0.07
    _bh
    0.07
    Activations Density 0.026%

    No Known Activations