© 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. 26560
    Prev
    Next
    INDEX
    Explanations

    Rolette County

    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
    æĦĪ
    -0.07
    è¹Ń
    -0.07
    sia
    -0.06
    ãģĦãģ«
    -0.06
    æīijéĿ¢
    -0.06
    áĥ¥
    -0.06
    г
    -0.06
    åĨħ容æľī
    -0.06
    åıĪä¸įæĺ¯
    -0.06
    arium
    -0.06
    POSITIVE LOGITS
    ç¾İä¸Ń
    0.08
    æĶ¶èĹıæľ¬ç«Ļ
    0.08
    stor
    0.08
    ÑĪÑĤа
    0.08
    Tcp
    0.07
    @m
    0.07
    hof
    0.07
    è¦Ĩ
    0.07
    _coeffs
    0.07
    pter
    0.07
    Activations Density 0.001%

    No Known Activations