© 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. 19469
    Prev
    Next
    INDEX
    Explanations

    what comes next: or /

    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
    (
    -0.07
    åĢ¾åŁİ
    -0.06
    Q
    -0.06
    gai
    -0.06
    tk
    -0.06
    uck
    -0.06
    otype
    -0.06
    4
    -0.06
    éĽĦ
    -0.06
    0
    -0.06
    POSITIVE LOGITS
    arif
    0.09
    :selected
    0.08
    iseerd
    0.08
    ÉĻt
    0.08
    èses
    0.08
    irates
    0.08
    azgo
    0.08
    iento
    0.08
    zata
    0.08
    enska
    0.08
    Activations Density 0.001%

    No Known Activations