© 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. 50224
    Prev
    Next
    INDEX
    Explanations

    quantities or amounts

    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
    èĢĺ
    -0.10
    å¿ĥ缮ä¸Ń
    -0.09
    ç»´
    -0.09
    éĢĢå½¹
    -0.08
    å¤ĸæĿ¥
    -0.08
    æļĦ
    -0.08
    èĭij
    -0.08
    fos
    -0.08
    legen
    -0.08
    _ends
    -0.08
    POSITIVE LOGITS
    æķ°éĩı
    0.16
    çļĦæķ°éĩı
    0.15
     quantity
    0.14
     quantities
    0.13
    åħħ足
    0.13
     amounts
    0.12
    æ¯Ķä¾ĭ
    0.12
    æĢ»éĩı
    0.11
    æķ°é¢Ŀ
    0.11
    quantity
    0.10
    Activations Density 0.101%

    No Known Activations