© 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. 22697
    Prev
    Next
    INDEX
    Explanations

    http header options

    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
    微信æī«ä¸Ģæī«
    -0.09
    iciel
    -0.08
    alement
    -0.08
    erge
    -0.08
    _fx
    -0.08
    icial
    -0.08
    lest
    -0.08
    æĺ¯ä¸Ģé¢Ĺ
    -0.08
    åħ±åIJĮåĬªåĬĽä¸ĭ
    -0.08
    rtype
    -0.08
    POSITIVE LOGITS
    åĩł
    0.07
    æī£
    0.07
    æ´Ĺ
    0.06
    æ°¸
    0.06
     Just
    0.06
     just
    0.06
    éĿł
    0.06
    éĩĮçļĦ
    0.06
    è¿ij
    0.06
    aldas
    0.06
    Activations Density 0.873%

    No Known Activations