© 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. 62209
    Prev
    Next
    INDEX
    Explanations

    result of clinical or research

    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
    äºĶæĺŁ
    -0.10
    egin
    -0.08
    纪念
    -0.08
     gerne
    -0.08
    æĪIJ绩
    -0.08
     Hạ
    -0.07
    imulator
    -0.07
    ujÄħ
    -0.07
    éĶ¯
    -0.07
     hypoc
    -0.07
    POSITIVE LOGITS
    çļĦåĬªåĬĽ
    0.13
    åĬªåĬĽ
    0.11
     efforts
    0.11
    æĢĿèĢĥ
    0.11
    åħ±åIJĮåĬªåĬĽ
    0.11
     ëħ¸ëł¥
    0.10
    ç»ıèIJ¥æ´»åĬ¨
    0.10
    éķ¿ä¹ħ
    0.10
    ç¨
    0.10
    åģ¶çĦ¶
    0.09
    Activations Density 0.149%

    No Known Activations