© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50817
    Prev
    Next
    INDEX
    Explanations

    compilation errors

    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
    缨
    -0.10
    Boxes
    -0.09
    çŀĮ
    -0.09
    æĺ¯ä¸ĢåIJį
    -0.09
    èĢģ太太
    -0.09
    åĺĽ
    -0.09
     INTERN
    -0.09
    æĴ¼
    -0.09
    å®Įç¾İçļĦ
    -0.09
     Wordpress
    -0.08
    POSITIVE LOGITS
    æ´Ľ
    0.09
    utton
    0.08
    IRT
    0.08
    åĤįæĻļ
    0.08
    ideon
    0.08
    èIJ½
    0.08
    饱
    0.08
     %"
    0.08
    浸
    0.08
    è¸ı
    0.08
    Activations Density 0.190%

    No Known Activations