© 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. 57523
    Prev
    Next
    INDEX
    Explanations

    `/local` paths and system execution

    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
    åľ¨çº¿çķĻè¨Ģ
    -0.08
    orex
    -0.07
    åħį费注åĨĮ
    -0.07
    çľĭåľ¨
    -0.07
    æĪijçĪ¸
    -0.07
    ä¸įæĶ¹
    -0.07
    çĮ¬
    -0.07
    åĬłä»¥
    -0.07
    çİĭä¼Ł
    -0.07
    ÑģÑĤÑĢой
    -0.07
    POSITIVE LOGITS
    inho
    0.08
    alloc
    0.07
    itel
    0.07
    istro
    0.06
    _collect
    0.06
     Sandbox
    0.06
    èĪ±
    0.06
    置身
    0.06
    éĽĨä¸Ńç²¾åĬĽ
    0.06
    èĥ½åģļ
    0.06
    Activations Density 0.001%

    No Known Activations