© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41187
    Prev
    Next
    INDEX
    Explanations

    recent study or publication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <|box_end|>
    -0.08
     Medell
    -0.08
    ÙĥÙĨت
    -0.07
    ottie
    -0.07
    hots
    -0.07
    ?a
    -0.07
    æŃ»ç¥ŀ
    -0.07
     bâ
    -0.07
    irut
    -0.07
     Whites
    -0.07
    POSITIVE LOGITS
    âĢij
    0.08
    U
    0.07
    è¿ĩçĿĢ
    0.06
    æĭ¥
    0.06
     Cura
    0.06
    text
    0.06
    èĩªç«ĭ
    0.06
    िà¤ı
    0.06
    Bell
    0.06
     Ward
    0.06
    Activations Density 0.035%

    No Known Activations