© 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. 8303
    Prev
    Next
    INDEX
    Explanations

    pattern and related word endings

    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
    hyl
    -0.08
    abord
    -0.08
    åĽ½éŨ
    -0.08
    ROSS
    -0.08
    زاÙħ
    -0.07
    루
    -0.07
    zep
    -0.07
    kod
    -0.07
     comparatively
    -0.07
    _cast
    -0.07
    POSITIVE LOGITS
    è§Ħå¾ĭ
    0.12
    è¦ıå¾ĭ
    0.09
    åı¯å¾ª
    0.08
     patterns
    0.08
     pattern
    0.08
    è§Ħå¾ĭçļĦ
    0.07
    ä¹İ
    0.07
    checker
    0.06
    (pattern
    0.06
     закономеÑĢ
    0.06
    Activations Density 0.016%

    No Known Activations