© 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. 14423
    Prev
    Next
    INDEX
    Explanations

    zero-based indexing

    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
    åłĤåłĤ
    -0.08
    çIJĥèĽĭçĻ½
    -0.08
    owell
    -0.08
    uarte
    -0.08
    /WebAPI
    -0.07
    åĨ³
    -0.07
    ´Ģ
    -0.07
    æŁ¥çľĭ详ç»Ĩ
    -0.07
    illin
    -0.07
    çī¹å¼Ĥ
    -0.07
    POSITIVE LOGITS
    æĴ²
    0.07
    asers
    0.06
    æ·±å¤ĦçļĦ
    0.06
    aser
    0.06
    _representation
    0.06
    GRA
    0.06
    代为
    0.06
    รร
    0.06
    åĴ±ä»¬çļĦ
    0.06
    moz
    0.06
    Activations Density 0.002%

    No Known Activations