© 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. 13343
    Prev
    Next
    INDEX
    Explanations

    numeric lists followed by text

    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
    ,and
    -0.08
    ulls
    -0.07
    č↵č↵č↵
    -0.07
    éĹŃ
    -0.07
     Lastly
    -0.07
    ...).
    -0.06
    ä¾Ŀæ³ķ追究责任
    -0.06
     Barrett
    -0.06
    Č
    -0.06
    ;if
    -0.06
    POSITIVE LOGITS
    á»ĵi
    0.08
    lå
    0.08
    .inline
    0.07
    lage
    0.07
    UPLE
    0.07
    å¾Īæ¸ħæ¥ļ
    0.07
     Fak
    0.07
    dür
    0.07
    .jav
    0.07
    zion
    0.06
    Activations Density 0.019%

    No Known Activations