© 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. 42773
    Prev
    Next
    INDEX
    Explanations

    for the purposes

    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
    èĻ½çĦ¶åľ¨
    -0.08
    åIJĦå¤Ħ
    -0.07
     besides
    -0.07
    izan
    -0.07
    èĻ½çĦ¶æĺ¯
    -0.07
    èĢĮä¸įæĺ¯
    -0.06
    åŃIJæĽ°
    -0.06
    ť
    -0.06
    Tween
    -0.06
    i
    -0.06
    POSITIVE LOGITS
    heit
    0.08
    æľ¬é¢ĺ
    0.07
     humble
    0.07
    lore
    0.07
    here
    0.07
    ä»ĬåĽŀãģ¯
    0.07
    ,this
    0.07
    fia
    0.07
    è¿Ļ份
    0.07
    æĪij们è¿Ļ个
    0.07
    Activations Density 0.023%

    No Known Activations