© 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. 32992
    Prev
    Next
    INDEX
    Explanations

    by or make

    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
    æĸ°ç¤¾
    -0.08
    edo
    -0.08
    Storm
    -0.08
    acro
    -0.07
    chsel
    -0.07
    жÑij
    -0.07
    ç¢
    -0.07
    teken
    -0.07
    ÑĢож
    -0.07
    åıĤåĬłè¿ĩ
    -0.07
    POSITIVE LOGITS
    ä¼ijéĹ²å¨±ä¹IJ
    0.07
    ä¸İæݧåĪ¶
    0.06
    å¸ĥå±ĢåĴĮ
    0.06
    ä¿ĿçķĻäºĨ
    0.06
    ubre
    0.06
    ucha
    0.06
    ä¸¥æł¼éģµå®Ī
    0.06
    åĩºæīĭ
    0.06
    绣ä¸ĢæĪĺ线
    0.06
    umn
    0.06
    Activations Density 0.009%

    No Known Activations