© 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. 47779
    Prev
    Next
    INDEX
    Explanations

    initial

    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
    大è¡Ĺå°ıå··
    -0.07
    çĴŁ
    -0.07
     clearTimeout
    -0.07
    ohlen
    -0.07
     flexGrow
    -0.07
    reif
    -0.06
    è·ijå¾Ĺ
    -0.06
    -scrollbar
    -0.06
    éĢļåĪĻ
    -0.06
    yal
    -0.06
    POSITIVE LOGITS
    åĪĿå§ĭ
    0.31
     initial
    0.28
     Initial
    0.26
    initial
    0.26
    Initial
    0.25
     inicial
    0.25
     iniziale
    0.23
    _initial
    0.23
     initially
    0.21
    (initial
    0.21
    Activations Density 0.366%

    No Known Activations