© 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. 41214
    Prev
    Next
    INDEX
    Explanations

    US Treasury bonds

    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
    火热
    -0.07
    公共资源
    -0.07
    ...)↵
    -0.07
    惡
    -0.07
    moving
    -0.07
    膜
    -0.06
    แร
    -0.06
     solidarity
    -0.06
    滑
    -0.06
    ...)↵↵
    -0.06
    POSITIVE LOGITS
     ';'
    0.08
     glac
    0.07
    .inflate
    0.07
    そうな
    0.07
    낳
    0.06
    将自己的
    0.06
     tão
    0.06
    엎
    0.06
    aturas
    0.06
     Playoff
    0.06
    Activations Density 0.010%

    No Known Activations