© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64156
    Prev
    Next
    INDEX
    Explanations

    algebraic expressions coefficients

    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
    oha
    -0.06
    [d
    -0.06
    ytics
    -0.06
    ats
    -0.06
    太åı¤
    -0.06
    аÑĤÑĥ
    -0.06
    athon
    -0.06
     Sorg
    -0.06
    ä¸Ģå¥Ĺ
    -0.06
    Ãłng
    -0.05
    POSITIVE LOGITS
    éĺ¶
    0.08
     Casal
    0.08
    æĿĤ
    0.08
    omb
    0.07
    mpp
    0.07
    MessageType
    0.07
     thru
    0.07
     terms
    0.07
    ä¸įæĪIJ
    0.07
    ãĥıãĥ³ãĥī
    0.07
    Activations Density 0.013%

    No Known Activations