© 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. 7603
    Prev
    Next
    INDEX
    Explanations

    Twitter Handle, profile, SKU, Rank

    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
    被æµıè§Ī
    -0.09
    <|box_end|>
    -0.09
    spender
    -0.09
     candidature
    -0.09
    UnitTest
    -0.08
    Õ½
    -0.08
    ä¸ĭè½½æĬ¥åijĬ
    -0.08
    etu
    -0.08
     ë°ľìĥĿíķľ
    -0.08
    æݨèįIJæľ¬ä¹¦
    -0.07
    POSITIVE LOGITS
    -style
    0.07
    Style
    0.07
    authority
    0.07
     authority
    0.06
    ®
    0.06
    ä¸Ń人
    0.06
     reference
    0.06
    è®°äºĭ
    0.06
    人åIJį
    0.06
     #:
    0.06
    Activations Density 0.081%

    No Known Activations