© 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. 3944
    Prev
    Next
    INDEX
    Explanations

    So basically

    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
    ãģ¾ãģĹãģ¦
    -0.08
    egur
    -0.07
    ä¹ŁåĽłæѤ
    -0.07
    Å¡tÄĽ
    -0.07
    Ù°
    -0.07
    reis
    -0.07
    shaw
    -0.07
    è·¯éĢı
    -0.07
    à¹Į
    -0.07
    µ
    -0.07
    POSITIVE LOGITS
    -called
    0.12
    fter
    0.12
    éĹ®é¢ĺæĿ¥äºĨ
    0.10
    ftware
    0.08
    æĪij们æľī
    0.08
     everytime
    0.08
    forth
    0.08
    æĹłè®ºä»İ
    0.07
    bert
    0.07
    URITY
    0.07
    Activations Density 0.023%

    No Known Activations