© 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. 40022
    Prev
    Next
    INDEX
    Explanations

    code structure and keywords

    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
     nevertheless
    -0.08
    ãĥĬãĥ¼
    -0.07
    inel
    -0.07
    iales
    -0.07
    à¹Īวà¹Īา
    -0.07
    ationally
    -0.07
    é«ĺ度çļĦ
    -0.07
    лаÑģ
    -0.07
    edale
    -0.06
    çķ¥
    -0.06
    POSITIVE LOGITS
    寮
    0.08
    chied
    0.07
    åħĥèĢģ
    0.07
    æĺ¯ä¸ŃåĽ½
    0.07
    alanta
    0.07
    adura
    0.06
     :::
    0.06
    	   ↵
    0.06
    orro
    0.06
    ++++++++
    0.06
    Activations Density 0.006%

    No Known Activations