© 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. 34969
    Prev
    Next
    INDEX
    Explanations

    diodes, transistors, protection, short circuits

    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
    馥
    -0.09
     purity
    -0.09
    èĢĥå¯Ł
    -0.09
    ä¸īåĪĨ
    -0.09
    åĸĦ
    -0.09
    å¸ĥ
    -0.09
     dra
    -0.08
    VISIBLE
    -0.08
    æ¸ł
    -0.08
    åĴ«
    -0.08
    POSITIVE LOGITS
    æ³»
    0.10
     trÃŃ
    0.09
    æĤĦçĦ¶
    0.09
    /ns
    0.09
    lke
    0.09
    æĤ²ä¼¤
    0.09
    æijĶåĢĴ
    0.08
    è°IJ
    0.08
    溺
    0.08
    é»ĺé»ĺ
    0.08
    Activations Density 0.154%

    No Known Activations