© 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. 37918
    Prev
    Next
    INDEX
    Explanations

    introduces clauses

    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
    zil
    -0.07
    aben
    -0.07
     Mog
    -0.06
    éĤ£ä»ĸ
    -0.06
    èĦļ
    -0.06
    她表示
    -0.06
    leans
    -0.06
    é©
    -0.06
    æĪijåij¢
    -0.06
    éĤ£åı¥
    -0.06
    POSITIVE LOGITS
    yc
    0.07
    uz
    0.07
    ise
    0.07
    à¹ģหละ
    0.07
    fy
    0.07
    ucky
    0.07
     ONLY
    0.07
    æ¯ĵ
    0.07
    after
    0.07
    aked
    0.07
    Activations Density 0.071%

    No Known Activations