© 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. 27577
    Prev
    Next
    INDEX
    Explanations

    CT slice

    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
    åħ«æĸ¹
    -0.07
    angani
    -0.07
    жига
    -0.07
    anyi
    -0.07
    pid
    -0.07
    å¦į
    -0.07
    åĮ»éĻ¢åľ°åĿĢ
    -0.06
    rina
    -0.06
    ียร
    -0.06
    à²
    -0.06
    POSITIVE LOGITS
    è¶Ĭ
    0.08
    çĴ§
    0.08
    æīĢæıIJä¾ĽçļĦ
    0.08
    icato
    0.07
    utes
    0.07
    åįĩåĪĿ
    0.07
    edah
    0.07
    egen
    0.07
    alling
    0.06
    arton
    0.06
    Activations Density 0.155%

    No Known Activations