© 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. 49386
    Prev
    Next
    INDEX
    Explanations

    matrix dimensions, indices, and parameters

    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
    æĸ¹éĿ¢ä¹Ł
    -0.08
    åIJĦæľīåIJĦ
    -0.07
    orial
    -0.07
    æ´Ľæĸ¯
    -0.06
     sexes
    -0.06
    _fds
    -0.06
    æħ
    -0.06
    reno
    -0.06
    åķıãĤıãģļ
    -0.06
    åı¸
    -0.06
    POSITIVE LOGITS
    stal
    0.09
    ิà¸Ī
    0.07
    ev
    0.07
    ÑģÑĤÑĥпи
    0.07
    åĢ¾åŁİ
    0.07
    conut
    0.07
    [,
    0.07
    ä½łåħĪ
    0.07
    psilon
    0.07
    å®ģå¸Ĥ
    0.07
    Activations Density 0.005%

    No Known Activations