© 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. 51966
    Prev
    Next
    INDEX
    Explanations

    whenever, whilst, whether, those

    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
    çIJĨçĶ±æĺ¯
    -0.07
    TypeEnum
    -0.07
    足é¢Ŀ
    -0.07
    ÑĥÑīеÑģÑĤво
    -0.07
    ertoire
    -0.06
    èĭį天
    -0.06
    uktur
    -0.06
    ylation
    -0.06
    esis
    -0.06
    å°±åľ¨è¿ĻæŶ
    -0.06
    POSITIVE LOGITS
    åıĬéĶĢåĶ®
    0.08
    ä¼ļåĦ¿
    0.08
    elper
    0.08
    å°ĶçļĦ
    0.08
    æĪĸå¤ļ个
    0.08
    asm
    0.07
    º
    0.07
    ardy
    0.07
    åİ»ä½ķ
    0.07
    Msp
    0.07
    Activations Density 0.118%

    No Known Activations