© 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. 39156
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
    abay
    -0.07
    owed
    -0.07
     Gilbert
    -0.07
    ONTAL
    -0.07
     Patrol
    -0.07
     heel
    -0.07
    éĺµ
    -0.06
    çĶ¨çľ¼
    -0.06
    isi
    -0.06
    赵丽é¢ĸ
    -0.06
    POSITIVE LOGITS
    åŃĹ符
    0.08
    _PIPE
    0.07
    ichen
    0.07
    zec
    0.07
    slash
    0.07
    _escape
    0.07
    agt
    0.07
    _pipe
    0.07
     Pipe
    0.06
    pipes
    0.06
    Activations Density 0.034%

    No Known Activations