© 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. 56016
    Prev
    Next
    INDEX
    Explanations

    content: url: integrity= version: url: src= d:

    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
    kev
    -0.07
    ell
    -0.07
    elli
    -0.06
    ellis
    -0.06
    éĺ³æĺ¥
    -0.06
    -0.06
    æįı
    -0.06
    indr
    -0.06
    æĪijç»Īäºİ
    -0.06
    yps
    -0.06
    POSITIVE LOGITS
    /Branch
    0.09
    à´Łàµįà´Ł
    0.08
    alone
    0.08
    andalone
    0.08
    Pipeline
    0.07
    andle
    0.07
    \xc
    0.07
    ×ķ×IJ
    0.07
    -scenes
    0.07
    kaw
    0.07
    Activations Density 0.003%

    No Known Activations