© 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. 10268
    Prev
    Next
    INDEX
    Explanations

    Biography, Total Fat, All Professional

    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
    ,arg
    -0.07
    å©·
    -0.07
    é«ĺæ°Ķ
    -0.07
    åľ¨æŁIJäºĽ
    -0.06
    è¢ħ
    -0.06
     apprec
    -0.06
     "=",
    -0.06
    ?[
    -0.06
    itled
    -0.06
    วัล
    -0.06
    POSITIVE LOGITS
    åIJĪ计
    0.12
    æĢ»è®¡
    0.11
    åħ¶å®ĥ
    0.09
     totaal
    0.08
    åIJĮä¸Ĭ
    0.07
    TOTAL
    0.07
    åIJĪè¨Ī
    0.07
     ÐĴÑģего
    0.07
    ั
    0.07
     total
    0.07
    Activations Density 0.018%

    No Known Activations