© 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. 57849
    Prev
    Next
    INDEX
    Explanations

    `/**`

    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
    ================
    -0.12
    nable
    -0.10
    Ø©
    -0.10
    udiant
    -0.09
    sWith
    -0.09
    -0.09
    ยà¹Į
    -0.09
    ãĤº
    -0.09
    udir
    -0.09
    hund
    -0.09
    POSITIVE LOGITS
    身临åħ¶å¢ĥ
    0.12
    ä¸įåı¯æĢĿè®®
    0.12
    åĬłæĭ¿å¤§
    0.10
    对
    0.10
    äºĭåįĬåĬŁåĢį
    0.10
    ================================================================
    0.10
    à¸ģาร
    0.10
    缸è¾ħ缸æĪIJ
    0.09
    èĢ³çĨŁèĥ½è¯¦
    0.09
    æĸ°åĬłåĿ¡
    0.09
    Activations Density 0.060%

    No Known Activations