© 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. 51677
    Prev
    Next
    INDEX
    Explanations

    back to

    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
    eding
    -0.07
    è¿
    -0.06
    plx
    -0.06
    .Compute
    -0.06
    åĨįæľī
    -0.06
    heber
    -0.06
     Richt
    -0.06
    mozilla
    -0.06
    ³
    -0.06
    édé
    -0.06
    POSITIVE LOGITS
    ãģ«æĪ»
    0.13
     tadi
    0.10
     original
    0.09
     earlier
    0.09
    åĽŀåĪ°
    0.09
    original
    0.09
     zurück
    0.09
    æľĢåĪĿçļĦ
    0.09
     ursprüng
    0.09
    ãģ«æĪ»ãĤĭ
    0.08
    Activations Density 0.031%

    No Known Activations