© 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. 41777
    Prev
    Next
    INDEX
    Explanations

    early onset, earlier 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
    ä¸Ģæĸ°
    -0.08
     inmiddels
    -0.08
    /browse
    -0.08
    azz
    -0.07
    perfil
    -0.07
    Enumerable
    -0.07
    ä»ĸçİ°åľ¨
    -0.07
    æľĪèĩ³ä»Ĭ
    -0.07
    .Trace
    -0.07
    aum
    -0.07
    POSITIVE LOGITS
    æĹ©
    0.14
    æĹ©æĹ©
    0.12
    è¿ĩæĹ©
    0.12
    æıIJæĹ©
    0.11
     premature
    0.11
    æıIJåīį
    0.11
     precoce
    0.10
    æĽ´æĹ©
    0.10
    ä¸įæĹ©
    0.10
    è¾ĥæĹ©
    0.09
    Activations Density 0.124%

    No Known Activations