© 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. 62260
    Prev
    Next
    INDEX
    Explanations

    mutase, resolution, desymmetrization

    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
    çļĦæīĢæľīä½ľåĵģ
    -0.07
    डà¥Ģ
    -0.07
    .ly
    -0.07
    æķ°æį®æĿ¥æºIJ
    -0.07
    MISS
    -0.07
    attle
    -0.07
    неÑĨ
    -0.07
    astra
    -0.07
     Gund
    -0.07
    enius
    -0.07
    POSITIVE LOGITS
    wald
    0.08
     splitting
    0.08
     splits
    0.08
     split
    0.07
    æѧ
    0.07
    æĭĨåĪĨ
    0.07
     espont
    0.07
    Å¡no
    0.07
    åĪĨåĩº
    0.07
     disproportion
    0.07
    Activations Density 0.002%

    No Known Activations