© 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. 65326
    Prev
    Next
    INDEX
    Explanations

    circuit boards, red pill, noncanonical, Immunologic, CentOS, latter case

    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
    åIJĵ人
    -0.09
    htag
    -0.07
    иÑĤÑĥ
    -0.07
    çĩķ
    -0.07
    鼶åĶ®ä»·
    -0.07
    upon
    -0.07
    anga
    -0.07
    ãģĿãĤĮãģ«
    -0.07
     alike
    -0.07
    _survey
    -0.06
    POSITIVE LOGITS
    hos
    0.07
    çĢļ
    0.06
    çŃł
    0.06
    ìĿ´íĬ¸
    0.06
    elat
    0.06
     Alto
    0.06
    ине
    0.06
     part
    0.06
    ç²¾ç¥ŀä¸ĬçļĦ
    0.06
    åı¯æĥ³
    0.06
    Activations Density 0.171%

    No Known Activations