© 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. 34257
    Prev
    Next
    INDEX
    Explanations

    Plaintiff or plaint following punctuation

    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¸įå·®
    -0.08
    uret
    -0.08
    æĪijè¦ģè¯Ħ论
    -0.08
    ÙĨاÙĩ
    -0.08
    åİ»åIJ§
    -0.08
    agli
    -0.08
    æĬķèµĦé£İéĻ©
    -0.07
    æĮ¨
    -0.07
    ertino
    -0.07
    æĽ´æĸ°æĹ¥æľŁ
    -0.07
    POSITIVE LOGITS
    ICS
    0.07
    è¾ĵåħ¥çļĦ
    0.07
    INC
    0.06
    ä»
    0.06
    _REQUIRED
    0.06
    å¿ħéľĢ
    0.06
    å¾·ç½Ĺ
    0.06
    adata
    0.06
    輸åħ¥
    0.06
    Äģd
    0.06
    Activations Density 0.001%

    No Known Activations