© 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. 3599
    Prev
    Next
    INDEX
    Explanations

    smallcaps and abbreviations

    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
    cik
    -0.08
    rika
    -0.07
    æķĪæŀľçļĦ
    -0.07
    OwnProperty
    -0.07
    ced
    -0.07
    cest
    -0.06
    áĥĶáĥĹ
    -0.06
    lauf
    -0.06
    itone
    -0.06
    ged
    -0.06
    POSITIVE LOGITS
    äºĭåįĬåĬŁåĢį
    0.13
    缸è¾ħ缸æĪIJ
    0.13
    ä¸įåı¯æĢĿè®®
    0.13
    åħ¢åħ¢ä¸ļä¸ļ
    0.12
    åĭĩå¾Ģ缴åīį
    0.12
    俱ä¹IJéĥ¨
    0.12
    åĬłæĭ¿å¤§
    0.12
    身临åħ¶å¢ĥ
    0.11
    è·ĥè·ĥ欲è¯ķ
    0.11
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.11
    Activations Density 0.065%

    No Known Activations