© 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. 29216
    Prev
    Next
    INDEX
    Explanations

    merge or union

    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
    á»įi
    -0.07
    coder
    -0.07
    udeau
    -0.07
    ythe
    -0.07
    æ²ĥæĸ¯
    -0.07
    第ä¸Ģæī¹
    -0.07
    åĩĨå¤ĩ好çļĦ
    -0.07
    æĹ¥å¸¸çļĦ
    -0.07
    rame
    -0.07
    _adj
    -0.07
    POSITIVE LOGITS
    åIJĪ
    0.12
     shared
    0.09
    íķ©
    0.09
    shared
    0.09
    åIJĪ并
    0.08
     resulting
    0.08
     resultant
    0.07
    èĪį
    0.07
    Shared
    0.07
     composite
    0.07
    Activations Density 0.043%

    No Known Activations