© 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. 3463
    Prev
    Next
    INDEX
    Explanations

    providing service or information

    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
    ten
    -0.09
    第ä¸ĢæĿ¡
    -0.09
    éľĦ
    -0.08
    åĪĽç«ĭ
    -0.08
    ä¸ĢåĿĹ
    -0.08
    åįģæĿ¡
    -0.08
    å¾ĹåĪ°æľīæķĪ
    -0.08
    ä»Ģä¹Īåľ°æĸ¹
    -0.08
    lla
    -0.08
    _pdu
    -0.08
    POSITIVE LOGITS
    åIJ¹
    0.09
    æŁIJç§įç¨ĭ度
    0.08
    åı¯æĢľ
    0.08
    _assert
    0.08
    оÑĩ
    0.08
    è¯Ŀ说
    0.08
    erce
    0.08
    offs
    0.08
    åĬĿ
    0.08
    ulum
    0.08
    Activations Density 0.080%

    No Known Activations