© 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. 50219
    Prev
    Next
    INDEX
    Explanations

    blood type and antigens

    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
     amort
    -0.08
    è¿ijä¹īè¯į
    -0.08
    尺度
    -0.07
     Porn
    -0.07
     structured
    -0.07
     пÑĢоÑģÑĤÑĢан
    -0.07
     Justi
    -0.07
    วยา
    -0.06
    orent
    -0.06
    ải
    -0.06
    POSITIVE LOGITS
    è¡Ģåŀĭ
    0.10
     blood
    0.09
    çĮ®è¡Ģ
    0.09
     кÑĢови
    0.08
    è¾ĵè¡Ģ
    0.08
     genetic
    0.08
    éģĹä¼ł
    0.08
    çļĦè¡Ģ
    0.08
     Blood
    0.08
    è¡Ģ液
    0.08
    Activations Density 0.056%

    No Known Activations