© 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. 1387
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åĵij
    -0.07
     sekal
    -0.07
    cak
    -0.07
    umpl
    -0.07
    ä¹Łä¸įç®Ĺ
    -0.07
    为åħ¶
    -0.07
    lem
    -0.07
    æĸĩ件æĪĸ
    -0.06
    ä»»æķĻå¸Ī
    -0.06
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.06
    POSITIVE LOGITS
    stride
    0.07
    RIC
    0.07
    AGES
    0.07
    веÑĢи
    0.07
    æĸ¯å¡Ķ
    0.07
    ç»ĵ论
    0.07
    веÑĢ
    0.07
    edale
    0.07
    tees
    0.07
     Verf
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.