© 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. 50391
    Prev
    Next
    INDEX
    Explanations

    About

    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
    astra
    -0.12
    alet
    -0.10
    er
    -0.10
    ////////////
    -0.10
    ////////////////////////////////////////////////////////////////
    -0.09
    ities
    -0.09
    /her
    -0.09
    ervice
    -0.09
    ubin
    -0.08
    ymbols
    -0.08
    POSITIVE LOGITS
    ation
    0.10
    ÑģÑĤво
    0.09
    tingham
    0.09
    çijŁ
    0.08
    ed
    0.08
     ÙĪعÙĨ
    0.08
    ãģĬãĤĬãģ¾ãģĻ
    0.08
    ÑģÑı
    0.08
    able
    0.07
    ¡
    0.07
    Activations Density 0.132%

    No Known Activations