© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17522
    Prev
    Next
    INDEX
    Explanations

    specialized device +

    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
    å²±
    -0.07
    unn
    -0.07
    nie
    -0.06
    cze
    -0.06
    )(((
    -0.06
     Setia
    -0.06
    imme
    -0.06
    ä¸Ģå²ģ
    -0.06
     intelligence
    -0.06
    å¤Ħ女
    -0.06
    POSITIVE LOGITS
    åħ¬åı¸çŃī
    0.09
    æľįåĬ¡çŃī
    0.09
    管çIJĨçŃī
    0.08
    设å¤ĩçŃī
    0.08
    æ´»åĬ¨çŃī
    0.08
    ä¸Ńå¿ĥçŃī
    0.08
    +C
    0.08
    ä¿¡æģ¯çŃī
    0.07
    TOOLS
    0.07
    å·¥ç¨ĭçŃī
    0.07
    Activations Density 0.153%

    No Known Activations