© 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. 34424
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and specific 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
     ly
    -0.06
    /domain
    -0.06
    cer
    -0.05
    ลัà¸ģษà¸ĵà¹Į
    -0.05
    able
    -0.05
    -0.05
    éĴ®
    -0.05
    ;
    -0.05
    ç¼ł
    -0.05
    )
    -0.05
    POSITIVE LOGITS
    PathComponent
    0.10
    ResponseType
    0.10
    delen
    0.09
    幸ç¦ıå¿«ä¹IJ
    0.09
    uida
    0.09
    ÅĽci
    0.09
    PropTypes
    0.08
    åIJij她
    0.08
    udu
    0.08
    çIJ³å¨ľ
    0.08
    Activations Density 0.008%

    No Known Activations