© 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. 12850
    Prev
    Next
    INDEX
    Explanations

    `in from`

    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
    opoulos
    -0.07
    æĭīåħĭ
    -0.07
    nish
    -0.07
    æĺ¥æļĸ
    -0.07
    uzzi
    -0.07
     revan
    -0.07
    ucci
    -0.07
    gire
    -0.07
    _lite
    -0.07
    æľīæĿĥä¿ĿçķĻ
    -0.07
    POSITIVE LOGITS
    è¿ľåİ»
    0.07
    ihan
    0.07
    aug
    0.07
    ØŃدÙĬØ«
    0.06
    第ä¸īèĢħ
    0.06
    åįĥåįĥ
    0.06
    iphers
    0.06
    lesi
    0.06
     Pon
    0.06
     Casi
    0.06
    Activations Density 0.002%

    No Known Activations