© 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. 11534
    Prev
    Next
    INDEX
    Explanations

    college career

    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
    urry
    -0.08
    ly
    -0.07
    urre
    -0.07
    -reply
    -0.06
    URRE
    -0.06
    nya
    -0.06
    åħ¨åĽ½äººæ°ij
    -0.06
    æĺİçŁ¥
    -0.06
    Ø·ÙĬÙĨ
    -0.06
    veni
    -0.06
    POSITIVE LOGITS
    ász
    0.08
    ä¼ĹæīĢåij¨çŁ¥
    0.07
    ainless
    0.07
    codec
    0.07
    аÑĨи
    0.07
    áŀ¶áŀĵ
    0.07
     Aner
    0.07
    allows
    0.07
    ebra
    0.07
    tracer
    0.07
    Activations Density 0.399%

    No Known Activations