© 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. 50853
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    人
    -0.09
    ãģĬ
    -0.09
    ucle
    -0.08
    etwork
    -0.08
    er
    -0.08
    ãģĬãĤĤ
    -0.07
    人åĵģ
    -0.07
    人æĹı
    -0.07
    èĩªå·±
    -0.07
    cini
    -0.07
    POSITIVE LOGITS
    /from
    0.15
    /about
    0.14
    ़
    0.13
    TEN
    0.12
    à¹Ģหลว
    0.11
    icers
    0.11
    /by
    0.11
    allon
    0.11
    essional
    0.10
     sorts
    0.10
    Activations Density 2.117%

    No Known Activations