© 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. 18889
    Prev
    Next
    INDEX
    Explanations

    unexpected errors or failure handling

    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
    isco
    -0.07
    仪
    -0.07
    Relative
    -0.07
    çŃł
    -0.06
    .ft
    -0.06
     Relative
    -0.06
    .tm
    -0.06
    湿
    -0.06
    isc
    -0.06
    éľĢè¦ģç»ıè¿ĩ
    -0.06
    POSITIVE LOGITS
    ä¸ĩä¸Ģ
    0.09
    dal
    0.08
    <![
    0.08
    vre
    0.08
    ç¡®ä¿Ŀå®īåħ¨
    0.08
    ç¡®ä¿Ŀ
    0.08
    éĶħçĽĸ
    0.07
    æĪijçļĦçĶŁæ´»
    0.07
     unexpected
    0.07
    lest
    0.07
    Activations Density 0.010%

    No Known Activations