© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 714
    Prev
    Next
    INDEX
    Explanations

    browser, IE, sex, south

    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
    Negative Logits
    assin
    -0.07
    ç½ijåıĭè¯Ħ论
    -0.07
    èĬĿ
    -0.07
    éģĬ
    -0.07
    der
    -0.06
    éĤĦä¸į
    -0.06
    ä¸ĥåįģäºĮ
    -0.06
    erk
    -0.06
    à¹Ħà¸Ľà¸Ķà¹īวย
    -0.06
    çī¹å®ļ
    -0.06
    POSITIVE LOGITS
    åħ¶ä½Ļ
    0.16
    åħ¶é¤ĺ
    0.14
     оÑģÑĤалÑĮнÑĭÑħ
    0.13
     restantes
    0.13
     restante
    0.12
     оÑģÑĤалÑĮнÑĭе
    0.12
    çŃīåħ¶ä»ĸ
    0.11
    çļĦåħ¶ä»ĸ
    0.11
     ëĤĺ머ì§Ģ
    0.11
    åī©ä¸ĭçļĦ
    0.11
    Activations Density 0.205%

    No Known Activations