© 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. 55555
    Prev
    Next
    INDEX
    Explanations

    will find

    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
    ças
    -0.08
    è¾
    -0.08
    igh
    -0.08
    ì
    -0.07
    åħ¢åħ¢
    -0.07
    æı
    -0.07
     gew
    -0.07
     Built
    -0.07
    гÑĢаÑĦи
    -0.07
    æľ¬çº§
    -0.06
    POSITIVE LOGITS
    注æĦıçļĦæĺ¯
    0.09
    ibert
    0.07
    anine
    0.07
    bery
    0.07
    åģļçļĦæĺ¯
    0.07
    alda
    0.07
    à´ŁàµĨ
    0.07
    alma
    0.07
    byt
    0.07
    osal
    0.07
    Activations Density 0.022%

    No Known Activations