© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35940
    Prev
    Next
    INDEX
    Explanations

    event organise ceremonial

    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
    æľīæĿĥ
    -0.09
    çĮ¾
    -0.09
    误
    -0.09
    失
    -0.09
    acher
    -0.08
     mounts
    -0.08
    rac
    -0.08
    æĬ¬å¤´
    -0.08
    éĢŀ
    -0.08
    NECT
    -0.08
    POSITIVE LOGITS
    ç³»åĪĹæ´»åĬ¨
    0.12
    æ°Ķæ°Ľ
    0.11
    çļĦéŃħåĬĽ
    0.11
    æŃ¤æ¬¡æ´»åĬ¨
    0.10
    æħ°éĹ®
    0.10
    åºıå¹ķ
    0.09
    讲座
    0.09
    è¿ĽåĨĽ
    0.09
    主é¢ĺæ´»åĬ¨
    0.09
    oke
    0.09
    Activations Density 0.128%

    No Known Activations