© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19-RESID-POST-AA
    6. 7968
    Prev
    Next
    INDEX
    Explanations

    6 or 9

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -names
    -0.07
    +
    -0.07
    稍稍
    -0.07
     무엇
    -0.07
     הכול
    -0.07
     aprove
    -0.06
    巧克
    -0.06
     Corpor
    -0.06
    兔子
    -0.06
    ["_
    -0.06
    POSITIVE LOGITS
    !");↵
    0.07
     расход
    0.07
    防水
    0.07
     update
    0.07
     dry
    0.06
     offices
    0.06
    .firebaseapp
    0.06
    (Environment
    0.06
    唐
    0.06
     United
    0.06
    Activations Density 0.001%

    No Known Activations