© 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. 23641
    Prev
    Next
    INDEX
    Explanations

    matrix indices

    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
    /forum
    -0.08
    ä½ľä¸ºä¸Ģç§į
    -0.07
    æµij
    -0.07
    éĻIJãĤĬ
    -0.07
    .getBytes
    -0.06
     vectors
    -0.06
    åĽ¾æĸ¯
    -0.06
    èĽ
    -0.06
    æĨ§
    -0.06
    ç½ĹæĽ¼
    -0.06
    POSITIVE LOGITS
    .diag
    0.08
    åħ¬ç§ģ
    0.08
    innie
    0.08
    rilla
    0.07
    主
    0.07
    åĿ¦
    0.07
    éĥ¨ç½²
    0.07
    aupts
    0.07
    _principal
    0.07
    .di
    0.07
    Activations Density 0.002%

    No Known Activations