© 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. 21098
    Prev
    Next
    INDEX
    Explanations

    great people or healthy individuals

    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
    æĿ¨å®¶
    -0.07
    æĥ³è±¡çļĦ
    -0.07
    çĭ®åŃIJ
    -0.07
    çįħåŃIJ
    -0.07
    ESI
    -0.07
    ilog
    -0.07
    ä¹Łä¸įå¤ļ
    -0.06
    æĶĢçĻ»
    -0.06
     Vega
    -0.06
    Spacing
    -0.06
    POSITIVE LOGITS
    èĦ¯
    0.08
    ovit
    0.07
    è¡
    0.06
    toria
    0.06
    iates
    0.06
    áŁĭ
    0.06
     appell
    0.06
    maid
    0.06
    æĦĪ
    0.06
    å½¢æĪIJäºĨ
    0.06
    Activations Density 0.084%

    No Known Activations