© 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. 54755
    Prev
    Next
    INDEX
    Explanations

    way too

    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
    æľī个
    -0.10
    裨
    -0.10
    ç¥ī
    -0.09
    ôm
    -0.09
    梦è§ģ
    -0.09
    æľīä¸Ģ个
    -0.09
    åĴĮåıijå±ķ
    -0.09
    åŁºéĩijä¼ļ
    -0.09
    .quick
    -0.09
    éģµå¾ª
    -0.08
    POSITIVE LOGITS
    太è¿ĩ
    0.28
     too
    0.28
    太
    0.28
    太å¤ļ
    0.27
    太大
    0.26
    太å¤ļäºĨ
    0.25
    太å¤ļçļĦ
    0.25
    太é«ĺ
    0.25
    too
    0.24
     ÑģлиÑĪком
    0.23
    Activations Density 0.114%

    No Known Activations