© 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
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29760
    Prev
    Next
    INDEX
    Explanations

    typedef struct or unsigned

    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
    zzi
    -0.09
    åĭĥåĭĥ
    -0.09
    amental
    -0.08
    oglio
    -0.08
    ç¨İåĬ¡æĢ»å±Ģ
    -0.08
    louv
    -0.08
    ayani
    -0.08
    inness
    -0.08
    å°½æľī
    -0.08
    alet
    -0.08
    POSITIVE LOGITS
    ../../../
    0.08
    i
    0.08
    iant
    0.07
    iab
    0.07
    umper
    0.07
    ÛĮ
    0.07
    iance
    0.07
    ical
    0.07
    ÙĬÙĭا
    0.07
    Ģ
    0.07
    Activations Density 0.008%

    No Known Activations