Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 24616
    Prev
    Next
    INDEX
    Explanations

    harmful actions

    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
    (strcmp
    -0.07
     Edited
    -0.07
     University
    -0.07
     Mondays
    -0.07
     buffalo
    -0.06
    uggage
    -0.06
     pottery
    -0.06
    俾
    -0.06
     Passage
    -0.06
    _BLE
    -0.06
    POSITIVE LOGITS
     dav
    0.07
    תאריך
    0.07
    /business
    0.07
    备
    0.07
    保持
    0.06
     hẳ
    0.06
    _dependency
    0.06
    onedDateTime
    0.06
    工具
    0.06
    .return
    0.06
    Activations Density 0.005%

    No Known Activations