© 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. 7109
    Prev
    Next
    INDEX
    Explanations

    Physics/engineering concepts

    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
    最主要
    -0.07
     stirring
    -0.07
    𝜃
    -0.06
    ewolf
    -0.06
    移送
    -0.06
     yö
    -0.06
    董事
    -0.06
     dafür
    -0.06
     cider
    -0.06
    _clause
    -0.06
    POSITIVE LOGITS
    始建于
    0.07
    ䷸
    0.07
    求
    0.06
    变得更
    0.06
    $app
    0.06
    sub
    0.06
     Services
    0.06
    SERVER
    0.06
    thumbnails
    0.06
    小朋友
    0.06
    Activations Density 0.002%

    No Known Activations