© 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. 56768
    Prev
    Next
    INDEX
    Explanations

    valence bond

    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
    магни
    -0.08
    ä¸ĭæĮ«
    -0.08
    andr
    -0.08
    .unshift
    -0.07
    滾
    -0.07
    涨äºĨ
    -0.07
    软硬件
    -0.07
    ä¸ĭä¸ĢæĿ¡
    -0.07
    转载èĩ³
    -0.07
    anut
    -0.07
    POSITIVE LOGITS
    æĢ»ä»·
    0.10
    çĶ»æ³ķ
    0.09
    ritt
    0.08
     bond
    0.08
     allot
    0.08
    æijĬ
    0.08
     oxygen
    0.07
     diagrams
    0.07
    åİŁåŃIJ
    0.07
    满åłĤ
    0.07
    Activations Density 0.001%

    No Known Activations