© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 7298
    Prev
    Next
    INDEX
    Explanations

    gin or in

    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
    Autoresizing
    -0.07
    Modal
    -0.07
    蹂
    -0.07
     fights
    -0.06
    startswith
    -0.06
    大洋
    -0.06
    _WH
    -0.06
     allele
    -0.06
    .getElement
    -0.06
     editorial
    -0.06
    POSITIVE LOGITS
    熘
    0.07
    ぜ
    0.07
     xuất
    0.06
    深刻
    0.06
    桧
    0.06
    地标
    0.06
    enal
    0.06
    绿地
    0.06
    ран
    0.06
     PlayStation
    0.06
    Activations Density 0.002%

    No Known Activations