© 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. 64058
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by descriptive word/phrase

    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
    èĢĮéĢłæĪIJ
    -0.08
    erk
    -0.08
    chas
    -0.07
    èĢĮ没æľī
    -0.07
    èĢĮ导èĩ´
    -0.07
    eload
    -0.07
     ê²½ìļ°ìĹIJëĬĶ
    -0.07
    æĺ¯æ²¡æľī
    -0.07
    ersist
    -0.07
    -0.07
    POSITIVE LOGITS
     same
    0.09
     possible
    0.08
    æĹ¥èµ·æĸ½è¡Į
    0.07
    åı¯åģļ
    0.07
     posible
    0.07
    åIJĮä¸Ĭ
    0.07
    æĹłæĺİæĺ¾
    0.07
    /=
    0.07
     no
    0.07
    éļ¾åº¦å¤§
    0.07
    Activations Density 0.061%

    No Known Activations