© 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. 1245
    Prev
    Next
    INDEX
    Explanations

    grade 12

    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
    en
    -0.07
    Õ£
    -0.06
    ä¸įå¤ĸ
    -0.06
    çļĨ
    -0.06
    äd
    -0.06
    ä¸įå®ĮçļĦ
    -0.06
    .co
    -0.06
    INAS
    -0.06
    å¹´å§ĭ
    -0.06
    ','.
    -0.06
    POSITIVE LOGITS
    EEDED
    0.09
    ouden
    0.08
    Spoiler
    0.08
    iews
    0.08
    oulos
    0.08
    oces
    0.08
    /type
    0.07
    cules
    0.07
    å§ĭèĩ³ç»Ī
    0.07
    /column
    0.07
    Activations Density 0.237%

    No Known Activations