© 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. 16643
    Prev
    Next
    INDEX
    Explanations

    for better or worse

    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
    odic
    -0.09
    åķ¬
    -0.09
    æĻ°
    -0.08
    åĨľåľº
    -0.08
    èħ¹
    -0.08
    ica
    -0.08
    oretical
    -0.08
    ication
    -0.07
    çĩĥ
    -0.07
    _supported
    -0.07
    POSITIVE LOGITS
    çľł
    0.10
    meld
    0.09
    ék
    0.09
     Consort
    0.09
    屯
    0.09
    ndef
    0.09
    mtime
    0.09
    éĥ½
    0.09
    _mime
    0.09
    éĢ¼
    0.09
    Activations Density 0.020%

    No Known Activations