© 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. 41707
    Prev
    Next
    INDEX
    Explanations

    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
    为什么要
    -0.07
    ******↵↵
    -0.07
    -)
    -0.06
     dd
    -0.06
     demás
    -0.06
    ILED
    -0.06
    zM
    -0.06
    接受了
    -0.06
    ]=>
    -0.06
     wishlist
    -0.06
    POSITIVE LOGITS
     Zone
    0.08
     Electricity
    0.07
    .Locale
    0.07
    urança
    0.07
    belief
    0.07
    措施
    0.07
    \Factory
    0.07
    (wallet
    0.06
    الت
    0.06
    scaling
    0.06
    Activations Density 0.002%

    No Known Activations