© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51448
    Prev
    Next
    INDEX
    Explanations

    look no further

    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
    åIJĦç§įåIJĦæł·
    -0.10
    æľªæĪIJ
    -0.10
    çĽ¸å¯¹è¾ĥ
    -0.09
    æļĹ示
    -0.09
    æ®ĭçķĻ
    -0.09
    央ä¼ģ
    -0.09
    éķ¿å¯¿
    -0.09
    ÑģоÑģ
    -0.08
    Cancellation
    -0.08
    gaard
    -0.08
    POSITIVE LOGITS
     nothing
    0.20
    ä¸įèĥ½åĨį
    0.18
     nowhere
    0.17
    nothing
    0.17
    没æľīä»Ģä¹Ī
    0.17
    ä¸įå¾Ĺ
    0.16
    åĨįä¹Łæ²¡æľī
    0.16
     никак
    0.15
     Nothing
    0.15
     NOTHING
    0.15
    Activations Density 0.074%

    No Known Activations