© 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. 48412
    Prev
    Next
    INDEX
    Explanations

    copyright and license

    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
    bern
    -0.12
    еÑĢÑĮ
    -0.11
    客åİħ
    -0.09
    å¹³æĿ¿
    -0.09
    antine
    -0.09
    åħ¹
    -0.08
    è±ĨæµĨ
    -0.08
    ä¸įåĨį
    -0.08
    æµĵ
    -0.08
    è¸ıå®ŀ
    -0.08
    POSITIVE LOGITS
    DataSet
    0.08
    注
    0.08
    åī©ä¸ĭçļĦ
    0.08
    å¨Ī
    0.08
    éĴ
    0.08
    aint
    0.08
    ç°ª
    0.07
    棹
    0.07
     Malk
    0.07
    åĿIJä¸ĭ
    0.07
    Activations Density 0.290%

    No Known Activations