© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18586
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and geometry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    亿ä¸ĩ
    -0.10
    ãģ©ãģĵãĤį
    -0.09
    åĥļ
    -0.09
    享
    -0.09
    æĴij
    -0.09
    æ¢ĵ
    -0.09
     ÑĢазв
    -0.09
    çŃ¹éĽĨ
    -0.09
    visual
    -0.09
    .visual
    -0.09
    POSITIVE LOGITS
    å½¢çĬ¶
    0.10
     shapes
    0.10
     shape
    0.10
     vol
    0.09
    å°ıåŃIJ
    0.08
    æĢª
    0.08
    .shape
    0.08
    èĿĪ
    0.08
    fort
    0.08
    /ge
    0.08
    Activations Density 0.038%

    No Known Activations