© 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. 12711
    Prev
    Next
    INDEX
    Explanations

    math theory

    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
    å©¿
    -0.07
     Allian
    -0.07
     emissions
    -0.07
    isnan
    -0.07
    .weixin
    -0.07
    avy
    -0.07
    жай
    -0.06
    -ret
    -0.06
    ç½²
    -0.06
     Tham
    -0.06
    POSITIVE LOGITS
    riz
    0.08
    åı¨
    0.08
    talk
    0.07
     notions
    0.07
     Constructs
    0.07
    DG
    0.07
     Tits
    0.07
    oser
    0.07
     talk
    0.07
     folklore
    0.07
    Activations Density 0.222%

    No Known Activations