© 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. 59050
    Prev
    Next
    INDEX
    Explanations

    put something

    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
    andy
    -0.09
    edition
    -0.08
    cape
    -0.08
    keit
    -0.08
    ousel
    -0.08
    orso
    -0.08
    Ñĥй
    -0.08
    æ¯Ķäºļ
    -0.08
    hoven
    -0.08
    undy
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.10
    HOLDER
    0.08
    èĩ
    0.08
    妥å½ĵ
    0.08
    æıĽãģĪ
    0.07
    tlement
    0.07
     aside
    0.07
     semula
    0.07
    holders
    0.07
    ioned
    0.07
    Activations Density 0.095%

    No Known Activations