© 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. 18713
    Prev
    Next
    INDEX
    Explanations

    origin client

    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
    IDD
    -0.08
    ://%
    -0.08
    arcz
    -0.07
    heid
    -0.07
    .za
    -0.07
    _LITERAL
    -0.07
    LEV
    -0.07
    endig
    -0.06
    BufferData
    -0.06
    -strokes
    -0.06
    POSITIVE LOGITS
    管çIJĨçŃī
    0.08
    åħ¬åı¸çŃī
    0.07
    æľįåĬ¡çŃī
    0.07
    {}".
    0.07
    گاÙĩÛĮ
    0.07
    pcodes
    0.06
    æĪijåIJ§
    0.06
    头çŃī
    0.06
    {}'.
    0.06
    æĪijåIJĹ
    0.06
    Activations Density 0.159%

    No Known Activations