© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62754
    Prev
    Next
    INDEX
    Explanations

    matrix representations, conditional independence

    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
    bose
    -0.07
    ghan
    -0.07
    Ä«m
    -0.07
    ivs
    -0.07
    ä¹ħä¹ħ
    -0.07
    .geom
    -0.07
    åĽĽå¤Ħ
    -0.06
    zaÅĦ
    -0.06
    rosse
    -0.06
    æīĢæ¶īåıĬ
    -0.06
    POSITIVE LOGITS
    åľ¨æ²¡æľī
    0.18
    åľ¨æľª
    0.14
    åľ¨æĹł
    0.13
    åľ¨ä¸į
    0.12
     conditional
    0.12
    åľ¨æľī
    0.12
    à¸łà¸²à¸¢à¹ĥà¸ķà¹ī
    0.11
    åīįæıIJæĺ¯
    0.11
    æĿ¡ä»¶ä¸ĭçļĦ
    0.10
     à¸łà¸²à¸¢à¹ĥà¸ķà¹ī
    0.10
    Activations Density 0.227%

    No Known Activations