© 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. 27985
    Prev
    Next
    INDEX
    Explanations

    tons and tonnes

    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
    ä¸Ģå¥Ĺ
    -0.10
    æľ¬ç½ij
    -0.10
    å¥ī
    -0.10
    éĨħ
    -0.09
    ä¸Ģè¶Ł
    -0.09
    ourd
    -0.09
    deen
    -0.09
    	TokenName
    -0.09
    .ArgumentParser
    -0.09
    rup
    -0.09
    POSITIVE LOGITS
    纸ä¸Ĭ
    0.09
    lion
    0.09
    éĴ¢æĿIJ
    0.08
    studio
    0.08
    é»ijçĻ½
    0.08
     lion
    0.08
    sett
    0.08
    ëĶ°
    0.08
    å°¤åħ¶æĺ¯
    0.08
    éĵģè·¯
    0.08
    Activations Density 0.007%

    No Known Activations