© 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. 17911
    Prev
    Next
    INDEX
    Explanations

    not followed by common words

    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
    让人们
    -0.10
    ä¹Łç®Ĺæĺ¯
    -0.09
    ä¸įå¾Ĺä¸į说
    -0.09
     limb
    -0.09
    æĽ´åĥıæĺ¯
    -0.09
    并ä¸įæĺ¯
    -0.09
    ken
    -0.09
    使人
    -0.08
    (nil
    -0.08
    ivi
    -0.08
    POSITIVE LOGITS
    uye
    0.09
    èĢĮå·²
    0.09
    withstanding
    0.08
    è¿«
    0.08
    oriously
    0.08
    éĢĶ
    0.08
    æħ¨
    0.08
    ially
    0.08
    _SYN
    0.08
    æĶ¶æ¬¾
    0.08
    Activations Density 0.033%

    No Known Activations