© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21151
    Prev
    Next
    INDEX
    Explanations

    contour lines, locations, neighborhoods

    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
    æ··æ²Į
    -0.09
    æµij
    -0.09
    éĴ»çłĶ
    -0.08
    åįĥåı¤
    -0.08
    æĹºåŃ£
    -0.08
    çıł
    -0.08
    è´¢åĬ¡ç®¡çIJĨ
    -0.08
    äºıæįŁ
    -0.08
    åĮĹéĥ¨
    -0.08
    æĭ±
    -0.08
    POSITIVE LOGITS
    æĨ©
    0.09
    oints
    0.08
    临
    0.08
    çļĦä½įç½®
    0.08
     contours
    0.08
    åĭĥ
    0.08
    å¸ĪèĮĥ
    0.08
    ä¸Ģå¤ľ
    0.08
    æĶ¾ä¸ĭ
    0.08
    åĪĨå¸ĥ
    0.08
    Activations Density 0.169%

    No Known Activations