© 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. 47784
    Prev
    Next
    INDEX
    Explanations

    teams, fighters, candidates

    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
    ä¸ĭæīĭ
    -0.10
    æĬ¬èµ·
    -0.09
    icken
    -0.09
    æIJĶ
    -0.09
    åıªè¦ģä½ł
    -0.09
    åIJĮå¿Ĺ们
    -0.09
    å¤ļ人
    -0.08
    çĬĢ
    -0.08
    æĬ¬
    -0.08
    ä¸Ģ人
    -0.08
    POSITIVE LOGITS
    åIJĦæľī
    0.13
    åıĮæĸ¹
    0.13
    åIJĦèĩªçļĦ
    0.12
    åIJĦèĩª
    0.12
     sides
    0.10
    éĥ½æľī
    0.10
     mad
    0.10
    éĥ½æľīèĩªå·±
    0.10
    -sided
    0.09
    mad
    0.09
    Activations Density 0.083%

    No Known Activations