© 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. 43658
    Prev
    Next
    INDEX
    Explanations

    data format or structure

    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
    ãĤıãģĸ
    -0.06
    亲èĩª
    -0.06
    _IDLE
    -0.06
    举
    -0.06
    å¤ļåıij
    -0.06
    issan
    -0.06
    elv
    -0.06
    è¿IJçŃ¹
    -0.06
     Rookie
    -0.06
    неÑĨ
    -0.05
    POSITIVE LOGITS
    以便äºİ
    0.10
     usable
    0.10
    便äºİ
    0.09
    以å¤ĩ
    0.09
     afterwards
    0.09
    -ready
    0.09
     useful
    0.09
     uncompressed
    0.09
    -format
    0.09
    æĸ¹ä¾¿
    0.09
    Activations Density 0.265%

    No Known Activations