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. 2680
    Prev
    Next
    INDEX
    Explanations

    search

    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
    襁
    -0.07
    Expect
    -0.07
    Triple
    -0.07
    ཚ
    -0.06
    stdin
    -0.06
    😺
    -0.06
    انتخاب
    -0.06
    ʤ
    -0.06
    razil
    -0.06
    年第
    -0.06
    POSITIVE LOGITS
    rí
    0.07
    හ
    0.07
     Brigham
    0.07
    perature
    0.07
    สวม
    0.07
     GLenum
    0.07
     eCommerce
    0.07
    .Unique
    0.06
    _characters
    0.06
     Mormon
    0.06
    Activations Density 0.017%

    No Known Activations