© 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. 29057
    Prev
    Next
    INDEX
    Explanations

    code initialization syntax

    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
    ern
    -0.07
    itten
    -0.07
    ild
    -0.07
    manship
    -0.07
    tern
    -0.07
    sey
    -0.07
    æĺİçĻ½
    -0.07
    æĢİæł·åģļ
    -0.07
    婪
    -0.07
    è·µ
    -0.06
    POSITIVE LOGITS
    LOCKS
    0.07
    OutputStream
    0.07
    istet
    0.07
    ocoder
    0.07
    athom
    0.07
    ugat
    0.06
    à¹Īาย
    0.06
     бед
    0.06
    locker
    0.06
    æĬĺèµ·
    0.06
    Activations Density 0.006%

    No Known Activations