© 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. 8476
    Prev
    Next
    INDEX
    Explanations

    # placeholders

    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
    æĪĸå¤ļ个
    -0.10
    à§įস
    -0.10
    à§įতà§ģ
    -0.08
    rific
    -0.08
    rence
    -0.08
    zicht
    -0.08
    åij»
    -0.08
    usz
    -0.08
    isons
    -0.08
    踵
    -0.08
    POSITIVE LOGITS
     noqa
    0.11
    s
    0.10
    !/
    0.09
    ï¸ı
    0.08
    einander
    0.08
    ////////////////////////////////////////////////////////////
    0.07
    ifdef
    0.07
    ////////////////////////////////////////////////////////////////
    0.07
    ir
    0.07
    san
    0.07
    Activations Density 0.162%

    No Known Activations