© 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. 22688
    Prev
    Next
    INDEX
    Explanations

    numbers separated by commas

    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
    æµĴ
    -0.08
    rano
    -0.07
    conomy
    -0.07
    çī¹æĸ¯
    -0.07
    toa
    -0.06
    rana
    -0.06
    æĢİä¹Ī说
    -0.06
     بات
    -0.06
    Ratio
    -0.06
    ivre
    -0.06
    POSITIVE LOGITS
     etc
    0.10
    etc
    0.09
    Å«k
    0.08
     заблÑĥ
    0.07
     повÑĸд
    0.07
     Ñħолоди
    0.07
    idades
    0.07
     кине
    0.07
    interop
    0.07
    yman
    0.07
    Activations Density 0.044%

    No Known Activations