© 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. 38328
    Prev
    Next
    INDEX
    Explanations

    release options anytime

    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
    èIJ½æ°´
    -0.08
    onia
    -0.07
     Jaya
    -0.07
    è¾Ľåĭ¤çļĦ
    -0.06
    .nlm
    -0.06
    ä¸ĢçŃ¹
    -0.06
    ä½ķä¸į
    -0.06
     Kan
    -0.06
     polled
    -0.06
    è¿ĩå¤ľ
    -0.06
    POSITIVE LOGITS
     terminates
    0.08
    cleanup
    0.08
    ä¸Ģç»ı
    0.08
    ä»»éĢī
    0.08
     künd
    0.07
    ingleton
    0.07
    termination
    0.07
    _sections
    0.07
     exerc
    0.07
    inality
    0.07
    Activations Density 0.024%

    No Known Activations