© 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. 32106
    Prev
    Next
    INDEX
    Explanations

    jQuery code 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
    viso
    -0.08
    usada
    -0.07
    ably
    -0.07
    etas
    -0.07
    arro
    -0.07
    ../../../
    -0.07
    roma
    -0.07
    ugna
    -0.07
    haus
    -0.07
    yard
    -0.07
    POSITIVE LOGITS
    nya
    0.09
    0.08
    ï¸ı
    0.07
    ç¥Ł
    0.07
     (![
    0.07
    oppable
    0.07
    nest
    0.07
    ecycle
    0.07
    [email
    0.07
    tiin
    0.07
    Activations Density 0.005%

    No Known Activations