© 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. 38556
    Prev
    Next
    INDEX
    Explanations

    dictionary keys

    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
    Ø©
    -0.14
    es
    -0.09
    ино
    -0.09
    ÏĤ
    -0.09
    ingly
    -0.08
    sWith
    -0.08
    秫
    -0.08
    oja
    -0.08
    èĢĮå°±
    -0.08
    aeda
    -0.08
    POSITIVE LOGITS
    èī²åĪĹ
    0.08
    身临åħ¶å¢ĥ
    0.08
    äººä¸ºæľ¬
    0.08
     #:
    0.07
    è·ĥè·ĥ欲è¯ķ
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    ãģµãģĨãģ«
    0.06
    ìĿĺ
    0.06
     ':
    0.06
    nection
    0.06
    Activations Density 0.016%

    No Known Activations