© 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. 21275
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

    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
    äºĨ解ä¸ĭ
    -0.07
     O
    -0.07
    è¿ŀäºij
    -0.06
    æµģç»ı
    -0.06
     false
    -0.06
    out
    -0.06
    IGO
    -0.06
     black
    -0.06
    atable
    -0.06
    ç¯
    -0.06
    POSITIVE LOGITS
    dek
    0.09
    è¯Ĭ
    0.08
    arang
    0.08
     //~
    0.08
    arnation
    0.08
     dagegen
    0.08
    á»ķ
    0.07
    -commit
    0.07
    getApplication
    0.07
    ç½
    0.07
    Activations Density 0.081%

    No Known Activations