© 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. 64824
    Prev
    Next
    INDEX
    Explanations

    well-being, care, knowledge, expectedness, specific job, worldwide scale, routine practice

    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
    ç½ijç«Ļ导èĪª
    -0.10
    utang
    -0.10
    engi
    -0.09
    æķ´æ²»å·¥ä½ľ
    -0.09
    åİĭåĬĽå¤§
    -0.08
    ertest
    -0.08
    çĻ½éª¨
    -0.08
    éģ¥éģ¥
    -0.08
    ToEnd
    -0.08
    æī¶è´«å·¥ä½ľ
    -0.08
    POSITIVE LOGITS
    æĪĸ
    0.08
    (
    0.07
    olut
    0.07
    ___
    0.07
    ↵
    0.07
    -
    0.06
     or
    0.06
    oods
    0.06
    æĢ§æĪĸ
    0.06
    0.06
    Activations Density 0.005%

    No Known Activations