© 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. 40801
    Prev
    Next
    INDEX
    Explanations

    shape or round

    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
    广ä¹ī
    -0.08
    ç¿Ķ
    -0.07
     Fai
    -0.07
     intim
    -0.07
    åī¥
    -0.06
    缴åij¼
    -0.06
    dul
    -0.06
    uldig
    -0.06
     gated
    -0.06
     Watkins
    -0.06
    POSITIVE LOGITS
     rounded
    0.11
     rounding
    0.11
    å®ŀéĻħæĵįä½ľ
    0.09
     rounds
    0.09
    rounded
    0.09
    round
    0.09
    æķ´æķ°
    0.09
    åĩij
    0.09
     round
    0.08
    _round
    0.08
    Activations Density 0.017%

    No Known Activations