© 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. 57432
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    ä¿ł
    -0.07
    stown
    -0.07
     délais
    -0.07
    esthes
    -0.06
    bh
    -0.06
     VÆ°Æ¡ng
    -0.06
     Tie
    -0.06
    oter
    -0.06
    stitut
    -0.06
    å·¥æľŁ
    -0.06
    POSITIVE LOGITS
     Burr
    0.07
    oday
    0.07
     circol
    0.07
    èĤ´
    0.07
    éļľ
    0.07
    loor
    0.07
    rag
    0.07
    åİĨ
    0.06
    жеÑĢ
    0.06
    weif
    0.06
    Activations Density 0.057%

    No Known Activations