© 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. 9264
    Prev
    Next
    INDEX
    Explanations

    lines, lines, asympt, cycles, placeholder

    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
    éķ¿å¤Ħ
    -0.07
    /photos
    -0.07
    äºĮ人çļĦ
    -0.07
    è¢«æŁ¥
    -0.07
    墩
    -0.07
    Endian
    -0.07
    ayload
    -0.07
    ä½łæĺ¯è°ģ
    -0.07
    å®Į
    -0.07
    eled
    -0.07
    POSITIVE LOGITS
     lines
    0.09
    lines
    0.09
    -lined
    0.08
    éķ¿æľŁä½¿çĶ¨
    0.08
    å¤ļæĿ¡
    0.07
     asympt
    0.07
    ause
    0.07
    çĽ´çº¿
    0.07
     Guill
    0.07
     линий
    0.07
    Activations Density 0.006%

    No Known Activations