© 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. 14893
    Prev
    Next
    INDEX
    Explanations

    filter conversion circuit components

    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
    ftar
    -0.07
    离ä¸įå¼Ģ
    -0.07
    thon
    -0.07
    æĬĹæű
    -0.07
    ä¸ŃåĮº
    -0.07
    roat
    -0.07
    ç¼¥
    -0.07
    onais
    -0.07
    ourke
    -0.06
    è¿Ľè¡ĮæIJľç´¢
    -0.06
    POSITIVE LOGITS
    åĪĨæµģ
    0.10
    éĺ»æĮ¡
    0.10
    /filter
    0.09
    éĺ»
    0.09
    éĺ»æĸŃ
    0.09
    æĮ¡ä½ı
    0.08
     inserted
    0.08
    æĭ¦ä½ı
    0.08
    éĺ»æĭ¦
    0.08
     delaying
    0.08
    Activations Density 0.045%

    No Known Activations