© 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. 45352
    Prev
    Next
    INDEX
    Explanations

    consequence and implication

    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
    表达å¼ı
    -0.07
    akon
    -0.07
    欢è¿İåIJĦä½į
    -0.06
     âĨĶ
    -0.06
    追éļı
    -0.06
     undef
    -0.06
    wers
    -0.06
    åį«åĽ½
    -0.06
    ัà¹īà¸Ļ
    -0.06
     Unlike
    -0.06
    POSITIVE LOGITS
    æĢ»åħ±
    0.14
     total
    0.13
    æĢ»
    0.12
    æĢ»çļĦ
    0.11
    total
    0.10
    æķ´æķ´
    0.09
    -total
    0.09
     Total
    0.09
    _total
    0.09
    Total
    0.09
    Activations Density 0.017%

    No Known Activations