© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29747
    Prev
    Next
    INDEX
    Explanations

    own, himself, his own

    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
    ä¹ĭä¹ħ
    -0.09
    orman
    -0.08
    ĺ
    -0.08
    udou
    -0.08
    ãģįãģ®
    -0.08
    apak
    -0.08
    моÑĤÑĢов
    -0.08
    gether
    -0.08
    amá
    -0.08
    ä¹ĭæģĭ
    -0.07
    POSITIVE LOGITS
    -même
    0.11
    hood
    0.09
    ergestellt
    0.08
    lijke
    0.08
    verständlich
    0.07
    /her
    0.07
    thic
    0.07
    çļĦä¸Ģå¥Ĺ
    0.07
    lessness
    0.07
    ë§ĮìĿĺ
    0.07
    Activations Density 0.002%

    No Known Activations