© 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. 36733
    Prev
    Next
    INDEX
    Explanations

    assist, help, schedule, hear

    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
    赫
    -0.09
    çĿ¢
    -0.09
    ä¸ĵ项è¡ĮåĬ¨
    -0.09
    æĽ´å¤ļçļĦæĺ¯
    -0.09
    æľĢå¿«
    -0.09
    çİĭæĻĵ
    -0.09
    èĪĤ
    -0.08
    èĥ½æī¾åĪ°
    -0.08
    ä¸įåı¯éģ¿åħį
    -0.08
    iras
    -0.08
    POSITIVE LOGITS
    çķ´
    0.09
    assin
    0.09
    uri
    0.09
    åīįèĢħ
    0.09
    帮åĬ©
    0.08
     DISCLAIMER
    0.08
    é¢Ħ订
    0.08
    è¦ģä¹Ī
    0.08
    reasonable
    0.08
    解éĩĭ
    0.08
    Activations Density 0.009%

    No Known Activations