© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6210
    Prev
    Next
    INDEX
    Explanations

    select word or phrase

    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
    Negative Logits
    thest
    -0.09
    ðŁı»
    -0.09
    åįģ足
    -0.09
    æł·åŃIJ
    -0.09
    ware
    -0.09
    -labelledby
    -0.09
    ض
    -0.09
    amentals
    -0.09
    -quarters
    -0.09
    ernet
    -0.08
    POSITIVE LOGITS
    ively
    0.16
    ivity
    0.13
     lá»įc
    0.12
    eer
    0.10
    ivities
    0.10
    -purpose
    0.10
    ìĺµ
    0.10
    ately
    0.09
    æľĹ
    0.09
     lá»±a
    0.09
    Activations Density 0.088%

    No Known Activations