© 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. 57705
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    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
    éĺ¿å§Ĩ
    -0.07
    ØŃÙĩ
    -0.07
    _stdio
    -0.07
    _ms
    -0.07
     Subs
    -0.07
     xô
    -0.07
    jemu
    -0.06
    isses
    -0.06
     سÙĬر
    -0.06
     res
    -0.06
    POSITIVE LOGITS
    åĪĩå®ŀåģļ好
    0.08
    anguage
    0.07
    agoon
    0.07
    fic
    0.07
    ä¸ĸçķĮä¸ĬæľĢ大çļĦ
    0.07
    letal
    0.07
    à¸Ħุม
    0.07
    azzi
    0.06
    vaart
    0.06
    è¦ģåħħåĪĨ
    0.06
    Activations Density 0.004%

    No Known Activations