© 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. 56226
    Prev
    Next
    INDEX
    Explanations

    general + noun

    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
    æļĤæŶ
    -0.09
    ä¹Łå¸ĮæľĽ
    -0.09
    ä¸Ģç¬ij
    -0.09
     вÑģего
    -0.08
    åıªæĺ¯
    -0.08
    迦
    -0.08
    æīĢéľĢè¦ģ
    -0.08
    èĢģ头
    -0.08
    ä¸Ģå¾ĭ
    -0.08
    ego
    -0.08
    POSITIVE LOGITS
     xuyên
    0.10
    é¢Ĩä¼ļ
    0.10
    çļĦæĦŁè§ī
    0.09
    izations
    0.09
    æĦıä¹īä¸Ĭ
    0.09
    verständlich
    0.09
    ization
    0.09
    åħļå§Ķ
    0.09
    ifest
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.09
    Activations Density 0.030%

    No Known Activations