© 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. 62555
    Prev
    Next
    INDEX
    Explanations

    section names

    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
    essin
    -0.07
    ä¸įåı¯æĢĿè®®
    -0.07
    åħ°å¾·
    -0.07
    .cent
    -0.07
     fixed
    -0.07
    andas
    -0.06
    åĽºå®ļ
    -0.06
    arn
    -0.06
    /cop
    -0.06
    ativ
    -0.06
    POSITIVE LOGITS
    avour
    0.08
    |--
    0.08
    缸æ¯Ķä¹ĭä¸ĭ
    0.08
     tø
    0.07
    -->
    0.07
     Haji
    0.07
    uki
    0.07
    çĪ±æĺ¯
    0.07
     Guerrero
    0.07
    awai
    0.07
    Activations Density 0.002%

    No Known Activations