© 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. 8556
    Prev
    Next
    INDEX
    Explanations

    variable assignment or definition

    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
    çĿģ
    -0.07
    ForEach
    -0.07
    zor
    -0.06
    asuk
    -0.06
    æĽ¿ä»ĸ
    -0.06
    |%
    -0.06
    ç¾İæľ¯é¦Ĩ
    -0.06
    uca
    -0.06
    æ²»
    -0.06
    å°±ä¸į
    -0.06
    POSITIVE LOGITS
    æ°´èįī
    0.09
    ä¸įåıĺ
    0.09
    alin
    0.08
    _mgr
    0.07
    å¿ħä¸įåı¯
    0.07
     unchanged
    0.07
    à¹Ģà¸Ķียวà¸ģัà¸Ļ
    0.07
     Exerc
    0.07
    ä¸įè®Ĭ
    0.07
    same
    0.07
    Activations Density 0.040%

    No Known Activations