© 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. 8324
    Prev
    Next
    INDEX
    Explanations

    individuals and organizations

    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
    缸è¾ħ缸æĪIJ
    -0.08
    els
    -0.08
    istentes
    -0.08
    ê¹IJ
    -0.07
    äºĭåįĬåĬŁåĢį
    -0.07
    pes
    -0.07
    ÙĬع
    -0.07
    ëĮĢë¡ľ
    -0.07
    зо
    -0.07
    äºİå¿ĥ
    -0.07
    POSITIVE LOGITS
    hood
    0.11
    /groups
    0.10
    /group
    0.09
    ividual
    0.09
    æĪĸå°ı
    0.08
    åĴĮç»Ħç»ĩ
    0.08
    /team
    0.08
     whose
    0.08
    /
    0.08
    ized
    0.07
    Activations Density 0.022%

    No Known Activations