© 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. 10969
    Prev
    Next
    INDEX
    Explanations

    programming and coding related terms

    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
     fra
    -0.08
    ä»įçĦ¶æĺ¯
    -0.08
    é«ĺå°Ķ
    -0.08
    åīįæīĢ
    -0.08
    ä»įçĦ¶
    -0.08
    羣å¿ĥ
    -0.08
    æµģéĩı
    -0.08
     Drag
    -0.08
    åºĦ
    -0.08
     Dra
    -0.08
    POSITIVE LOGITS
    ationally
    0.10
    è¿ĻçĤ¹
    0.09
    unting
    0.09
    師
    0.09
    æīĵä»Ĺ
    0.09
    å°ıçĻ½
    0.09
     Languages
    0.09
    人åijĺ
    0.09
    å°ıåŃIJ
    0.09
    [Any
    0.09
    Activations Density 0.088%

    No Known Activations