© 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. 38308
    Prev
    Next
    INDEX
    Explanations

    programming syntax or keywords

    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
    agic
    -0.08
    trak
    -0.08
    aged
    -0.07
    æĺ¯åIJĹ
    -0.07
    aging
    -0.07
    Intern
    -0.07
    vard
    -0.07
    irchen
    -0.06
    åĩ«
    -0.06
    ç´§æĢ¥
    -0.06
    POSITIVE LOGITS
    ä¿¡å¿ĥåĴĮ
    0.08
    usher
    0.07
    åħ¬åı¸åıĬ
    0.07
    èĬ³èįī
    0.07
    å©Ĩ
    0.07
    ingly
    0.06
    mani
    0.06
    æĦ§
    0.06
    inson
    0.06
    unks
    0.06
    Activations Density 0.001%

    No Known Activations