© 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. 22483
    Prev
    Next
    INDEX
    Explanations

    left, actual, width, city

    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
    ing
    -0.07
    èį«
    -0.07
    _RCC
    -0.07
    æ··
    -0.07
    ibert
    -0.06
    avia
    -0.06
    ix
    -0.06
    ane
    -0.06
    ó
    -0.06
    åĮĸçļĦ
    -0.06
    POSITIVE LOGITS
    arts
    0.08
    поÑĤе
    0.08
    ä»İéĩį
    0.08
    uplicates
    0.08
    èĸ¯
    0.08
     videor
    0.08
    äºĭåįĬåĬŁåĢį
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    менов
    0.07
    -shopping
    0.07
    Activations Density 0.226%

    No Known Activations