© 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. 40161
    Prev
    Next
    INDEX
    Explanations

    letter abbreviations

    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
    æŃ¤æ¥¼
    -0.07
    ä¸ĭå±Ĥ
    -0.06
    tev
    -0.06
    tti
    -0.06
    µľ
    -0.06
     sucker
    -0.06
    azzino
    -0.06
    tid
    -0.06
    :on
    -0.06
    imbus
    -0.06
    POSITIVE LOGITS
    åŃĹæ¯į
    0.18
     letter
    0.15
     letters
    0.14
    letter
    0.13
     alphabet
    0.13
     LETTER
    0.13
    Letter
    0.12
     Letter
    0.12
    letters
    0.12
    -letter
    0.12
    Activations Density 0.233%

    No Known Activations