© 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. 26276
    Prev
    Next
    INDEX
    Explanations

    `[layer`, `ML`, `can`

    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
    客
    -0.07
    eto
    -0.06
    æľºä¼ļ
    -0.06
    ee
    -0.06
     mom
    -0.06
    å·įå·į
    -0.06
     Kre
    -0.06
    .gov
    -0.06
     boo
    -0.06
    I
    -0.06
    POSITIVE LOGITS
    æĦļ人
    0.10
    itol
    0.09
    erek
    0.09
    [layer
    0.09
     continuidade
    0.09
    oplay
    0.09
    缸åħ³æĸ°éĹ»
    0.09
    è¿·ç³Ĭ
    0.08
    енÑģи
    0.08
    itada
    0.08
    Activations Density 0.012%

    No Known Activations