© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39642
    Prev
    Next
    INDEX
    Explanations

    medical conditions and anatomy

    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
    èĶ·
    -0.07
    iss
    -0.07
    oload
    -0.06
     doubt
    -0.06
    æĪijçŃī
    -0.06
    ãģĺãģ£ãģıãĤĬ
    -0.06
    umed
    -0.06
     infinit
    -0.06
    çİ°è¡Į
    -0.06
    umn
    -0.06
    POSITIVE LOGITS
     progressive
    0.08
    åı¯èĥ½åĩºçİ°
    0.08
    åı¯å¯¼èĩ´
    0.08
    åı¯æľī
    0.08
    ×ĵת
    0.08
     пÑĢогÑĢеÑģÑģи
    0.08
    容æĺĵåĩºçİ°
    0.07
     precip
    0.07
    åı¯èĥ½å¯¼èĩ´
    0.07
    è¹Ī
    0.07
    Activations Density 0.424%

    No Known Activations