© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 17127
    Prev
    Next
    INDEX
    Explanations

    Russian or Cyrillic characters

    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
    ...).
    -0.09
    !).
    -0.07
    ...",
    -0.07
    .):
    -0.07
     []).
    -0.07
    anson
    -0.07
    ...”
    -0.07
    !),
    -0.07
    !");
    -0.06
    :],
    -0.06
    POSITIVE LOGITS
    ç§«
    0.08
    åı±
    0.08
    lå
    0.08
     ìĹĨìĿĮ
    0.07
    รั
    0.07
    æľīåIJį
    0.07
     ãģªãģ©
    0.07
    оÑģÑĤÑĢе
    0.07
    cedure
    0.07
     Rodrig
    0.07
    Activations Density 0.036%

    No Known Activations