© 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. 27686
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
     asc
    -0.07
    éļ¾å¾Ĺ
    -0.07
    èµ
    -0.07
     solid
    -0.07
    åĽº
    -0.07
    éĴ¦
    -0.06
    tribution
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    Solid
    -0.06
    ä¸Ģ说
    -0.06
    POSITIVE LOGITS
    oš
    0.08
    è¿Ļ个æĺ¯
    0.08
     likewise
    0.08
    åıĪåIJį
    0.08
     swinger
    0.08
     hingegen
    0.08
    aign
    0.07
    yak
    0.07
    涯
    0.07
    yas
    0.07
    Activations Density 0.080%

    No Known Activations