© 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. 55346
    Prev
    Next
    INDEX
    Explanations

    groupId JSON

    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
     Certa
    -0.08
    aldo
    -0.08
    roma
    -0.07
    ä¹±ä¸ĸ
    -0.07
    obia
    -0.07
    att
    -0.07
    äg
    -0.07
    parseFloat
    -0.07
    uart
    -0.07
    èĤ¥æ²ĥ
    -0.07
    POSITIVE LOGITS
    åĸ¶
    0.07
    chette
    0.07
    arne
    0.06
    æĭ£
    0.06
    inth
    0.06
    æĸ¯é¡¿
    0.06
    ä¸īåIJį
    0.06
    å¸ĥæĸ¯
    0.06
    æ³īæ°´
    0.06
    樽
    0.06
    Activations Density 0.011%

    No Known Activations