© 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. 58691
    Prev
    Next
    INDEX
    Explanations

    scientific citations

    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
    laden
    -0.08
    itemid
    -0.07
     indes
    -0.07
    çī©ä»·å±Ģ
    -0.07
    _annotations
    -0.07
    ä¸Ģåıij
    -0.07
    æĹ¥ä¹ĭåīį
    -0.07
    setItem
    -0.07
     organisation
    -0.07
    mag
    -0.07
    POSITIVE LOGITS
    ç¼ī
    0.08
    èĭ¥å¹²æĦıè§ģ
    0.07
    秫
    0.07
    анда
    0.07
    HEMA
    0.07
    endent
    0.07
    anj
    0.07
    apor
    0.07
    <![
    0.07
    对æĪijåĽ½
    0.07
    Activations Density 0.014%

    No Known Activations