© 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. 56763
    Prev
    Next
    INDEX
    Explanations

    broadcasting or yield

    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
    æĻºåĬĽ
    -0.09
    å¯ĴåĨ·
    -0.09
    UND
    -0.09
     Airways
    -0.09
    çł»
    -0.09
    جÙĩ
    -0.09
    åĨ¬å¤©
    -0.09
    èĿ®
    -0.09
    åĿ¨
    -0.08
     Giov
    -0.08
    POSITIVE LOGITS
    è¯ī
    0.10
    éĢ¯
    0.09
    usan
    0.09
    кÑĢо
    0.09
    -rad
    0.09
    è²Į
    0.08
    red
    0.08
    /place
    0.08
    æ¯ıä¸Ģä½į
    0.08
    rophy
    0.08
    Activations Density 0.003%

    No Known Activations