© 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. 38751
    Prev
    Next
    INDEX
    Explanations

    ANT UNITED

    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
    ùn
    -0.07
     amm
    -0.07
    Âł
    -0.07
    unk
    -0.07
    inc
    -0.07
    é£İåIJ¹
    -0.07
    ++++
    -0.07
    chem
    -0.06
    %%%
    -0.06
    ä¸Ļ
    -0.06
    POSITIVE LOGITS
    纶
    0.08
     Zaj
    0.08
     Tahu
    0.07
    ä¸įçĶĺå¿ĥ
    0.07
    zioni
    0.07
    .family
    0.07
    realm
    0.07
    家人çļĦ
    0.07
    ัà¸į
    0.07
    éĻ¨èIJ½
    0.07
    Activations Density 0.145%

    No Known Activations