© 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. 23756
    Prev
    Next
    INDEX
    Explanations

    once every / daily / weekly / or twice

    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
    èŁ
    -0.09
    åĪ©åĻ¨
    -0.09
    nbsp
    -0.08
    è¿Ļæł·ä¸Ģ个
    -0.08
    çŃĸ
    -0.08
    ä¸Ģç³»åĪĹ
    -0.08
    ç®Ģ称
    -0.08
    ãģ°ãģĭãĤĬ
    -0.08
    okin
    -0.08
    大家åĪĨ享
    -0.08
    POSITIVE LOGITS
    åıĪä¸Ģ次
    0.11
    ìĶ©
    0.11
    åĩĭ
    0.10
     ForCanBeConvertedToForeach
    0.10
    åħ¨æĸ°çļĦ
    0.10
    å¾Īæľī
    0.09
    ÑĤин
    0.09
    /single
    0.09
    æĪĸå¤ļ
    0.09
    åĴİ
    0.09
    Activations Density 0.018%

    No Known Activations