© 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. 24096
    Prev
    Next
    INDEX
    Explanations

    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
    ัà¸ĩ
    -0.08
    hes
    -0.07
    á´
    -0.07
    ä¿¡ä»»
    -0.07
    åIJİèħ¿
    -0.07
    igur
    -0.07
    ERGE
    -0.07
    纷
    -0.07
    olg
    -0.07
    ç¡®
    -0.06
    POSITIVE LOGITS
     alast
    0.07
    æłĩè¯Ĩçłģ
    0.07
    ?id
    0.06
    ixel
    0.06
    饶
    0.06
     dá»ĭch
    0.06
    俱ä¹IJéĥ¨
    0.06
    <|box_end|>
    0.06
    æ±ķ
    0.06
    æĸ©èİ·
    0.06
    Activations Density 0.021%

    No Known Activations