© 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. 55058
    Prev
    Next
    INDEX
    Explanations

    eligibility or sufficiency

    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
    ä¸įåı¯èĥ½çļĦ
    -0.07
    åĶ¯
    -0.07
    ä»»ä½ķä¿Ŀè¯ģ
    -0.07
     inad
    -0.07
    kait
    -0.07
    çļĤ
    -0.07
    ä½Ĩåıªè¦ģ
    -0.07
    ields
    -0.07
    æĮĸæİĺåħ¬åı¸
    -0.07
    åĨįä¹Łä¸į
    -0.07
    POSITIVE LOGITS
    æľīè¶³å¤ŁçļĦ
    0.14
    è¶³å¤ŁçļĦ
    0.13
    è¶³å¤Ł
    0.12
     sufficiently
    0.11
     suffisamment
    0.11
     enough
    0.10
     adequately
    0.10
     sufficient
    0.10
    å¤Ł
    0.10
    è¶³å¤ł
    0.10
    Activations Density 0.090%

    No Known Activations