© 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. 3182
    Prev
    Next
    INDEX
    Explanations

    commercial uses or school project

    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
     Rookie
    -0.08
    пÑĢÑĭ
    -0.07
    >({
    -0.07
    _globals
    -0.07
    agan
    -0.07
    adelphia
    -0.07
     rookies
    -0.07
    æĢ
    -0.07
    (es
    -0.07
    riba
    -0.07
    POSITIVE LOGITS
     formal
    0.08
    çĶ¨éĢĶ
    0.07
    Ñħо
    0.07
    éľĢè¦ģçļĦ
    0.07
     رسÙħÙĬ
    0.07
    å±ħå¤ļ
    0.07
    ä¼ģäºĭä¸ļåįķä½į
    0.06
    åIJĦçķĮ
    0.06
    åŃ¦æľ¯çłĶ究
    0.06
     Formal
    0.06
    Activations Density 0.039%

    No Known Activations