© 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. 7291
    Prev
    Next
    INDEX
    Explanations

    scored / won / added / target / judge

    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
    èĿĪ
    -0.09
    çĸ£
    -0.09
    bast
    -0.09
    odus
    -0.09
    asts
    -0.09
     Greenwich
    -0.08
    å·²ç»ıæĪIJ为
    -0.08
    èĩªçĦ¶èĢĮ
    -0.08
    opus
    -0.08
    æĹłè®º
    -0.08
    POSITIVE LOGITS
    è½®æµģ
    0.12
    åIJĦèĩª
    0.12
    åIJĦèĩªçļĦ
    0.10
    loor
    0.10
    éĥ½æľī
    0.09
    å³Ĵ
    0.09
    åIJĦæľī
    0.09
    æĪ¿
    0.09
    .imag
    0.09
    .touch
    0.08
    Activations Density 0.036%

    No Known Activations