© 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. 11354
    Prev
    Next
    INDEX
    Explanations

    for atom, ray, line

    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
    对äºİéĤ£äºĽ
    -0.07
    æİ
    -0.07
    -0.07
    éļħ
    -0.07
    ä»İä¸Ģ个
    -0.06
    —which
    -0.06
    prof
    -0.06
    ÑĥÑīе
    -0.06
     __
    -0.06
    ëĭ¬
    -0.06
    POSITIVE LOGITS
    subpackage
    0.08
    çļĦåIJĹ
    0.08
    &o
    0.08
    akra
    0.07
    ushima
    0.07
    ød
    0.07
    arca
    0.07
    åįģæĹ¥åĨħ
    0.07
    allo
    0.07
    stätte
    0.07
    Activations Density 0.002%

    No Known Activations