© 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. 33616
    Prev
    Next
    INDEX
    Explanations

    later subsequent became

    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
    è¿ĩåİ»çļĦ
    -0.10
    ä¹ĭåĪĿ
    -0.09
    åĿĿ
    -0.09
    åı¯ä¿¡
    -0.09
    è¡·
    -0.08
    gan
    -0.08
    ä¹ĭæŶ
    -0.08
    alem
    -0.08
    _KIND
    -0.08
    æĪĸ许æĺ¯
    -0.08
    POSITIVE LOGITS
    åIJİæĿ¥
    0.33
     later
    0.27
    å¾Įä¾Ĩ
    0.25
    æĹ¥åIJİ
    0.24
    åIJİç»Ń
    0.23
    later
    0.22
     eventually
    0.22
     eventual
    0.22
     Later
    0.21
    éļıåIJİ
    0.21
    Activations Density 0.191%

    No Known Activations