© 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. 51258
    Prev
    Next
    INDEX
    Explanations

    solve equations

    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
    ÖĦ
    -0.07
    اء
    -0.07
    اÙĨس
    -0.07
     Cooper
    -0.07
    esu
    -0.06
    inging
    -0.06
    æĽ´çĶŁ
    -0.06
     tơ
    -0.06
    ess
    -0.06
    ement
    -0.06
    POSITIVE LOGITS
    _SOL
    0.08
    ä¸ĢéĹ®
    0.08
    æĢ»æĪIJ
    0.08
    为éļ¾
    0.07
    _solver
    0.07
    è
    0.07
    åIJ¬åıĸäºĨ
    0.07
    emming
    0.06
     approached
    0.06
    .solve
    0.06
    Activations Density 0.018%

    No Known Activations