© 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. 25403
    Prev
    Next
    INDEX
    Explanations

    angle between two

    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
    åıijçİ°æľī
    -0.07
    utto
    -0.07
    audi
    -0.07
    onat
    -0.07
    åĵªéĩĮæľī
    -0.06
    éĢłåĮĸ
    -0.06
    åĽĽæĸ¹
    -0.06
     audi
    -0.06
    ersch
    -0.06
    वाद
    -0.06
    POSITIVE LOGITS
    eman
    0.09
     vectors
    0.09
    ä¸įæŃ£
    0.08
    _vectors
    0.08
    Lng
    0.08
    serter
    0.08
    vector
    0.07
     "\",
    0.07
    çŁ¢
    0.07
    çŁ¢éĩı
    0.07
    Activations Density 0.003%

    No Known Activations