© 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. 4420
    Prev
    Next
    INDEX
    Explanations

    punctuation and common words

    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
    wig
    -0.07
    夫æĸ¯åŁº
    -0.07
    enberg
    -0.07
    æĹłæ³ķ满足
    -0.07
    ypy
    -0.07
    èĢģæľīæīĢ
    -0.06
    åŁºæľ¬åħ»èĢģä¿ĿéĻ©
    -0.06
    owska
    -0.06
    æľªåıĬæŶ
    -0.06
    /tiny
    -0.06
    POSITIVE LOGITS
    ä»ĺ
    0.08
     بÙĨÙĬ
    0.08
    azio
    0.07
    åĨ·éĿĻ
    0.07
    å¼Ľ
    0.07
    çķ¥
    0.07
    é©°éªĭ
    0.07
    æ´»
    0.07
    æĸ°åŁİ
    0.07
    æ¦Ĥè¦ģ
    0.07
    Activations Density 0.005%

    No Known Activations