© 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. 9607
    Prev
    Next
    INDEX
    Explanations

    grid dimensions like 4x4

    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¸Ģ身
    -0.08
    .baidu
    -0.08
    ahoo
    -0.08
    年头
    -0.07
    å¥īè¡Į
    -0.07
    urgeon
    -0.07
    .call
    -0.07
     analogous
    -0.07
    éŨåħ³
    -0.07
    èĥĥçĹħ
    -0.07
    POSITIVE LOGITS
    endorf
    0.08
    ç½ijæł¼
    0.08
     grid
    0.08
    ctic
    0.07
    ENDOR
    0.07
    纵横
    0.07
    grid
    0.07
    _contents
    0.06
    .Rect
    0.06
     Grid
    0.06
    Activations Density 0.012%

    No Known Activations