© 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. 32500
    Prev
    Next
    INDEX
    Explanations

    option tags

    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
    ä»ĸçļĦ人
    -0.06
    çIJĨ
    -0.06
    alin
    -0.06
    ä»
    -0.06
    æģ
    -0.06
    -
    -0.06
    天æĸĩ
    -0.06
    ä¹Ī
    -0.06
    ãģ¨ãģĦãģĪãģ°
    -0.06
    å¾·æĸ¯
    -0.06
    POSITIVE LOGITS
    çŃīçŃī
    0.09
    irate
    0.08
    åı¦å¤ĸè¿ĺæľī
    0.08
    baum
    0.08
    åħ±è®¡
    0.08
    timo
    0.07
    .parseFloat
    0.07
    éĥ½æĺ¯éĿŀ常
    0.07
    è¿ĺæľīå¾Īå¤ļ
    0.07
    ç¬ijåĤ²
    0.07
    Activations Density 0.079%

    No Known Activations