© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50859
    Prev
    Next
    INDEX
    Explanations

    NEW, _unix, publisher, ground, behind, Resource, left, above

    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
    é©»
    -0.10
    åĩĮ
    -0.09
    欢
    -0.09
    é¦ĸåıij
    -0.09
    æīİæł¹
    -0.09
    aÄŁ
    -0.09
    urm
    -0.09
    ollapse
    -0.09
    ä¸įä¸ĭ
    -0.09
    одеÑĢж
    -0.09
    POSITIVE LOGITS
    svn
    0.09
    èĢĮæĿ¥
    0.09
    éĥĽ
    0.09
     boss
    0.08
    å¹´èµ·
    0.08
    åģļèµ·
    0.08
    å¯Ł
    0.08
    åĬŀäºĭ
    0.08
    åĩºåıij
    0.08
    emes
    0.08
    Activations Density 0.121%

    No Known Activations