© 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. 8235
    Prev
    Next
    INDEX
    Explanations

    lists of items or numbers

    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
    漫
    -0.08
    DEFINED
    -0.08
    _SAVE
    -0.08
    åķ¤
    -0.07
    _DENIED
    -0.07
    æĽ´æ·±
    -0.07
     keyof
    -0.07
    abbrev
    -0.07
    éħ¸ç¢±
    -0.07
    èĢĮæŃ»
    -0.07
    POSITIVE LOGITS
    ä»İå°ıåĪ°å¤§
    0.08
    suma
    0.08
     progressive
    0.08
    éĢĴ
    0.07
    åĬłæ³ķ
    0.07
    æ·»åĬł
    0.07
     exponential
    0.07
    åı¯çĶ¨äºİ
    0.07
     enables
    0.07
     sums
    0.07
    Activations Density 0.005%

    No Known Activations