© 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. 27134
    Prev
    Next
    INDEX
    Explanations

    deal, attributes, networks, users, console

    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
     (
    -0.07
    attes
    -0.07
    _readable
    -0.07
    onen
    -0.06
    åĽłä¸ºè¿Ļ个
    -0.06
    è¯¥ä½ľèĢħ
    -0.06
    omers
    -0.06
    èѬå¦Ĥ
    -0.06
    ring
    -0.06
    _PATCH
    -0.06
    POSITIVE LOGITS
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.08
    éĻ¤å¤ĸ
    0.08
    湧
    0.08
    trup
    0.08
    .memo
    0.07
    ncer
    0.07
     genannt
    0.07
    zier
    0.07
    èģ
    0.07
    áĢ¬
    0.07
    Activations Density 0.057%

    No Known Activations