© 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. 42902
    Prev
    Next
    INDEX
    Explanations

    first item in a list

    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
    opro
    -0.07
    åįģåĪĨ
    -0.06
    å·
    -0.06
    lain
    -0.06
    ameni
    -0.06
    NEW
    -0.06
    γκ
    -0.06
    inaldo
    -0.06
    anker
    -0.06
    鸿
    -0.06
    POSITIVE LOGITS
    é¦ĸåħĪæĺ¯
    0.11
    é¦ĸåħĪåľ¨
    0.09
    ãģ¾ãģļ
    0.09
    第ä¸Ģ课
    0.09
    第ä¸ĢæŃ¥
    0.09
    第ä¸Ģéĺ¶æ®µ
    0.09
    第ä¸Ģ段
    0.08
    é¦ĸåħĪ
    0.08
    第ä¸Ģ项
    0.08
    먼
    0.08
    Activations Density 0.012%

    No Known Activations