© 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. 30974
    Prev
    Next
    INDEX
    Explanations

    code formatting and strings

    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
    serter
    -0.07
    oke
    -0.07
    okes
    -0.07
    kowski
    -0.07
    ataka
    -0.07
    etter
    -0.07
    æĪªçĦ¶
    -0.07
    raga
    -0.07
    .prevent
    -0.07
    ilon
    -0.07
    POSITIVE LOGITS
     details
    0.08
    åŁºæľ¬ä¿¡æģ¯
    0.08
    _misc
    0.07
    èĭ¥æľī
    0.07
    èĭ¥æĺ¯
    0.07
    _info
    0.07
    åīª
    0.07
    .summary
    0.06
     kompak
    0.06
    æĻ´
    0.06
    Activations Density 0.079%

    No Known Activations