© 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. 47083
    Prev
    Next
    INDEX
    Explanations

    supervise, train, downstream, child, pupils

    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
    ä¸įåĪ°
    -0.08
    à¸ī
    -0.07
    æıĴ
    -0.07
    /fw
    -0.07
    对大家
    -0.07
    irage
    -0.07
    aln
    -0.07
    é¢ijé¢ij
    -0.07
    _trim
    -0.07
    ä¿ĿåŃĺåĪ°
    -0.07
    POSITIVE LOGITS
    åĴĮèĩªå·±
    0.11
    ä¸ĭ级
    0.10
     subordinate
    0.10
    å¼Ł
    0.10
    åŃIJåŃĻ
    0.10
    æ¯Ķèĩªå·±
    0.10
    ä¸ĭå±ŀ
    0.10
    è·Łèĩªå·±
    0.09
     downstream
    0.09
    ä¸İèĩªå·±
    0.09
    Activations Density 0.273%

    No Known Activations