© 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. 52180
    Prev
    Next
    INDEX
    Explanations

    asked journalists questions

    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
     ngÄĥn
    -0.09
    аниз
    -0.09
    ä¸įä½Ĩ
    -0.09
    åIJ¦
    -0.09
    lys
    -0.09
    åı¬åĽŀ
    -0.09
    ä¹IJåĽ¢
    -0.09
    缴åįĩ
    -0.09
    åijĬ
    -0.08
    è¯ī
    -0.08
    POSITIVE LOGITS
    éĹ®ä»ĸ
    0.16
    æıIJéĹ®
    0.13
    éĹ®éģĵ
    0.13
    éĹ®
    0.13
    æݢ寻
    0.11
     asked
    0.11
    好å¥ĩ
    0.11
    æĥ³çŁ¥éģĵ
    0.11
    询éĹ®
    0.10
     question
    0.10
    Activations Density 0.072%

    No Known Activations