© 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. 9322
    Prev
    Next
    INDEX
    Explanations

    quotations and statements

    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
    ophone
    -0.08
    kering
    -0.08
    umper
    -0.08
    зне
    -0.07
    ulti
    -0.07
    _plain
    -0.07
    kers
    -0.07
    ারà§ĩ
    -0.07
    wana
    -0.07
    åijĹ
    -0.07
    POSITIVE LOGITS
    Call
    0.07
    人åĽŀå¤į
    0.06
    .call
    0.06
    if
    0.06
    æŃ¤ä¸º
    0.06
     коÑĢпÑĥ
    0.06
    ÑĻа
    0.06
    æĦīå¿«çļĦ
    0.06
    ull
    0.06
    ä¾ĽåĽ¾
    0.06
    Activations Density 0.032%

    No Known Activations