© 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. 21691
    Prev
    Next
    INDEX
    Explanations

    path finding and traversal

    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
    ç«£
    -0.08
    alah
    -0.08
    _typeof
    -0.07
    èĪ¹çĶ¨
    -0.07
    æĮijèµ·
    -0.07
    ArrayOf
    -0.07
    forums
    -0.07
    çŃī大
    -0.07
    ä¸IJ
    -0.07
    ListOf
    -0.07
    POSITIVE LOGITS
    åĮħæĭ¬
    0.10
    ä¸įåĮħæĭ¬
    0.09
     visited
    0.09
    breadcrumb
    0.08
     overlapping
    0.08
    including
    0.08
    éĩįåıł
    0.08
    沿éĢĶ
    0.08
    åºĶåĮħæĭ¬
    0.08
    éĩįåIJĪ
    0.08
    Activations Density 0.019%

    No Known Activations