© 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. 38792
    Prev
    Next
    INDEX
    Explanations

    information processing and theory

    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
    ekat
    -0.08
    kut
    -0.08
    ajian
    -0.08
    вÑı
    -0.08
    nji
    -0.07
    enom
    -0.07
    bersome
    -0.07
    æī¾ä¸įåĪ°
    -0.07
    èĩ
    -0.07
     Yayasan
    -0.07
    POSITIVE LOGITS
     information
    0.09
    çļĦä¿¡æģ¯
    0.09
     about
    0.08
    ä¿¡æģ¯
    0.08
    information
    0.08
    oust
    0.08
    ç¦Ģ
    0.08
     Information
    0.08
     nug
    0.07
    æĺ¯åħ³äºİ
    0.07
    Activations Density 0.012%

    No Known Activations