© 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. 12744
    Prev
    Next
    INDEX
    Explanations

    year flood signature program number

    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
    .Core
    -0.07
    haw
    -0.07
    ogos
    -0.07
    ÑĪаем
    -0.07
     Vanguard
    -0.07
    inos
    -0.07
    cke
    -0.07
    æĥ¨éģŃ
    -0.06
    åĪĿ
    -0.06
    inet
    -0.06
    POSITIVE LOGITS
    æĦıåij³çĿĢ
    0.22
     meaning
    0.19
    è¿ĻæĦıåij³çĿĢ
    0.19
    meaning
    0.16
     means
    0.16
     ознаÑĩаеÑĤ
    0.16
    æĦıæĢĿæĺ¯
    0.16
     Meaning
    0.16
    æĦıåij³èijĹ
    0.15
    çļĦæĦıæĢĿæĺ¯
    0.15
    Activations Density 0.037%

    No Known Activations