© 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. 12899
    Prev
    Next
    INDEX
    Explanations

    `//`

    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
    Äħc
    -0.07
    urgia
    -0.06
    à¸ķัà¸Ļ
    -0.06
    onese
    -0.06
    ymph
    -0.06
    ÑĤон
    -0.06
    stown
    -0.06
    zia
    -0.06
    .setTimeout
    -0.06
    .maximum
    -0.06
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.10
    ä½Ĩèĩ³å°ij
    0.08
     //
    0.07
    åįĹè¡Ĺ
    0.07
    ä¹ĻåıĮæĸ¹
    0.07
    åı¯æ¢¦
    0.07
    0.07
     ï½¢
    0.06
    **–
    0.06
    former
    0.06
    Activations Density 0.278%

    No Known Activations