© 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. 22684
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

    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
    åĨ³èµĽä¸Ń
    -0.08
    微信æī«ä¸Ģæī«
    -0.08
    ybrid
    -0.08
    conds
    -0.08
    apro
    -0.07
    èĥŃ
    -0.07
    icult
    -0.07
     aufs
    -0.07
    reiber
    -0.07
    è¡
    -0.07
    POSITIVE LOGITS
    çŃīåŁºæľ¬
    0.08
     HelloWorld
    0.08
    åĨĮ
    0.08
     foundational
    0.07
    basic
    0.07
    UID
    0.07
    åIJ¯èĴĻ
    0.07
    æľĢåŁºæľ¬çļĦ
    0.07
     Foundations
    0.07
    Peso
    0.07
    Activations Density 0.157%

    No Known Activations