© 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. 50692
    Prev
    Next
    INDEX
    Explanations

    reports and study

    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
    æĢª
    -0.07
    ||
    -0.07
     ~~
    -0.07
    磺
    -0.07
    LING
    -0.06
    èĩ´
    -0.06
     INC
    -0.06
    ils
    -0.06
    ius
    -0.06
    ä¸ĭ鼨
    -0.06
    POSITIVE LOGITS
    armo
    0.08
    arda
    0.08
    жÑij
    0.08
    ä¸ĥåįģäºĮ
    0.08
    å®īåħ¨æݪæĸ½
    0.07
    èĢĺ
    0.07
    ffet
    0.07
    rast
    0.07
    izu
    0.07
    contres
    0.07
    Activations Density 0.008%

    No Known Activations