© 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. 1947
    Prev
    Next
    INDEX
    Explanations

    concise, terse, minimalist

    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
    èse
    -0.06
    å¼ĢæĶ¾çļĦ
    -0.06
    ective
    -0.06
    chner
    -0.06
    çģµæ´»è¿IJçĶ¨
    -0.06
     shares
    -0.06
    æļĤ
    -0.06
    zio
    -0.06
    _SHARE
    -0.06
    elmes
    -0.06
    POSITIVE LOGITS
    ç®Ģæ´ģ
    0.10
    ç®ĢçŁŃ
    0.10
    ä¸Ģåı¥è¯Ŀ
    0.10
     terse
    0.09
    ç®Ģç®Ģåįķ
    0.09
     minimalis
    0.09
    ä¸Ģåı¥
    0.09
    æľĢå¿«çļĦéĢŁåº¦
    0.08
     concise
    0.08
     minimalist
    0.08
    Activations Density 0.034%

    No Known Activations