© 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. 64735
    Prev
    Next
    INDEX
    Explanations

    initializer/empty 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
    ansa
    -0.07
    iq
    -0.07
    áĬIJ
    -0.06
    ij
    -0.06
    è°·
    -0.06
     ÏĢαν
    -0.06
    å®Ĺ主
    -0.06
    èģĮ
    -0.06
    XL
    -0.06
    æĹłä¸į
    -0.06
    POSITIVE LOGITS
    koz
    0.09
    aped
    0.08
    è¿ĩä¸Ĭ
    0.08
    åľĪ
    0.08
    åIJĽå®ī
    0.08
    è¿ĩä¸Ģ个
    0.08
    æ·±åħ¥åľ°
    0.07
    [sizeof
    0.07
     Berb
    0.07
    UILayout
    0.07
    Activations Density 0.032%

    No Known Activations