© 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. 43746
    Prev
    Next
    INDEX
    Explanations

    is [subject of question]

    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
    elaar
    -0.08
    严
    -0.08
    रà¥įà¤Ł
    -0.07
    pc
    -0.07
    å¤ļå¾Ĺ
    -0.07
    kunst
    -0.07
    ä¸Ĭ访
    -0.07
    çIJ¥çıĢ
    -0.07
    à¥Ĥप
    -0.07
    ÑĢон
    -0.07
    POSITIVE LOGITS
    ç¬ijåĤ²
    0.08
    ife
    0.07
    ohlen
    0.06
    formatted
    0.06
    _MATH
    0.06
    _cum
    0.06
    éĸ²
    0.06
    å¹³éĺ³
    0.06
    lju
    0.06
    åĩĮ
    0.06
    Activations Density 0.002%

    No Known Activations