© 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. 10608
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è§Ĩè§Ĵ
    -0.10
    çıįçıł
    -0.10
     Elliot
    -0.10
    累累
    -0.09
    èĥĮæĻ¯
    -0.09
    æĦŁå®ĺ
    -0.09
    æĢĿè·¯
    -0.08
    ä¸ĸçķĮè§Ĥ
    -0.08
    lung
    -0.08
    åį°è±¡
    -0.08
    POSITIVE LOGITS
    è¿İ
    0.10
    èĪį
    0.10
     дÑĥÑħ
    0.10
    åĨĴéĻ©
    0.10
     spirit
    0.10
    esen
    0.10
    åįģ足
    0.10
    æĶ¹éĿ©åĪĽæĸ°
    0.09
    ãģ¾ãģ¾
    0.09
    éĿŀ常æĺİæĺ¾
    0.09
    Activations Density 0.008%

    No Known Activations