© 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. 52150
    Prev
    Next
    INDEX
    Explanations

    methods and approaches

    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
    Negative Logits
    abcdefghijkl
    -0.08
    ciar
    -0.08
    该楼å±Ĥçĸijä¼¼è¿Ŀè§Ħå·²è¢«ç³»ç»ŁæĬĺåıł
    -0.08
    触
    -0.08
    æĥ³æĸ¹
    -0.08
    plits
    -0.08
    ekret
    -0.08
    (:,:,
    -0.08
    endienst
    -0.08
    utsch
    -0.08
    POSITIVE LOGITS
     method
    0.10
     methods
    0.09
    method
    0.08
    Method
    0.08
     Method
    0.08
     tools
    0.08
    æĸ¹æ³ķ
    0.08
    _methods
    0.08
    çļĦæĸ¹æ³ķ
    0.08
    æīĭ段
    0.08
    Activations Density 0.074%

    No Known Activations