© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44210
    Prev
    Next
    INDEX
    Explanations

    levels or degrees

    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
    æĹłåıį
    -0.07
    iale
    -0.07
    ç½ijç«Ļåľ°åĽ¾
    -0.07
    æĸ¤
    -0.07
    åį³ä¾¿
    -0.07
    åį³ä½¿
    -0.07
    iali
    -0.07
    èĭ±
    -0.07
    æľĢä½³
    -0.07
     здÑĢа
    -0.06
    POSITIVE LOGITS
    ç¨ĭ度
    0.18
    ç¨ĭ度ä¸Ĭ
    0.18
    çļĦç¨ĭ度
    0.16
    ç¨ĭ度çļĦ
    0.15
     ìłķëıĦ
    0.11
    è¶Ĭä½İ
    0.11
     vs
    0.11
    度
    0.10
    è¶Ĭå°ij
    0.10
     versus
    0.10
    Activations Density 0.212%

    No Known Activations