© 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. 32038
    Prev
    Next
    INDEX
    Explanations

    greater than or less than

    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
    åĿİ
    -0.09
    èĢĮæѤæŶ
    -0.07
    ĮĢ
    -0.07
    atan
    -0.07
    ailer
    -0.07
    åķ¡
    -0.07
    ToObject
    -0.07
    ä»Ĭ天å°ıç¼ĸå°±
    -0.06
    è¿ľè¿ij
    -0.06
    outu
    -0.06
    POSITIVE LOGITS
    åĮħæĭ¬
    0.10
    (or
    0.10
     inclusive
    0.10
    æĪĸ
    0.09
     including
    0.09
     or
    0.09
     incluindo
    0.09
     inclusiv
    0.09
    æĪĸåħ¶
    0.09
    including
    0.09
    Activations Density 0.042%

    No Known Activations