© 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. 61931
    Prev
    Next
    INDEX
    Explanations

    digit and shape recognition

    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
    entials
    -0.07
    rav
    -0.07
    缴æİ¥åIJij
    -0.07
    å¾®éĩı
    -0.06
    èī²åĪĹ
    -0.06
    arez
    -0.06
    梯度
    -0.06
    åĪĨå±Ĥ
    -0.06
    è¿ĻæŃ£æĺ¯
    -0.06
    éģį
    -0.06
    POSITIVE LOGITS
     digit
    0.09
     shapes
    0.09
     upside
    0.09
    åĽ¾æ¡Ī
    0.09
    Shapes
    0.09
    digit
    0.09
    åŃĹå½¢
    0.08
    åģıæĹģ
    0.08
     shape
    0.08
    çļĦå½¢çĬ¶
    0.08
    Activations Density 0.020%

    No Known Activations