© 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. 21208
    Prev
    Next
    INDEX
    Explanations

    section headings or introductory words

    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
    è´µ
    -0.08
    de
    -0.07
    able
    -0.07
    aurus
    -0.07
    ade
    -0.07
    odelist
    -0.07
    ode
    -0.06
    oder
    -0.06
    CV
    -0.06
     vul
    -0.06
    POSITIVE LOGITS
    çļĦä¸įåIJĮ
    0.09
    anness
    0.09
    çļĦåģ¥åº·
    0.08
    มี
    0.08
    åħ¹
    0.08
    avid
    0.08
    нÑĭе
    0.08
    çļĦæľĢ大
    0.08
    ãģ®
    0.07
    çļĦéĩį
    0.07
    Activations Density 0.069%

    No Known Activations