© 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. 19781
    Prev
    Next
    INDEX
    Explanations

    rights to permit or prohibit

    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
    à²Ł
    -0.09
    è¿ĩå¾Ĺ
    -0.09
    工夫
    -0.09
    赤
    -0.09
    æģĥ
    -0.09
    大éĥ¨åĪĨ人
    -0.08
    egot
    -0.08
    HIR
    -0.08
    éĩİå¿ĥ
    -0.08
    å¼Ĭ
    -0.08
    POSITIVE LOGITS
    娥
    0.11
     лÑİбого
    0.09
    åĺ±
    0.09
     даже
    0.09
    çݳ
    0.09
    å±ĢéĿ¢
    0.09
    迳
    0.09
    å¤ļè¾¾
    0.09
    åģļä¸ĢäºĽ
    0.09
     sogar
    0.08
    Activations Density 0.056%

    No Known Activations