© 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. 20005
    Prev
    Next
    INDEX
    Explanations

    leukoplakia, assessment, stimulation

    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
    omen
    -0.07
    çĤľ
    -0.07
    flan
    -0.06
    avanaugh
    -0.06
    ãģĹãĤĩãģĨ
    -0.06
    elij
    -0.06
    _ten
    -0.06
    onds
    -0.06
    _MA
    -0.06
    ely
    -0.05
    POSITIVE LOGITS
    ä¹ĭ称çļĦ
    0.12
     poput
    0.11
    ì²´ìĿ¸
    0.11
     jakim
    0.11
    ìŀIJìĿ¸
    0.11
     вÑĢоде
    0.10
    诸å¦Ĥ
    0.09
     ([[
    0.09
     kuten
    0.09
    å¦Ĥ
    0.09
    Activations Density 0.294%

    No Known Activations