© 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. 64118
    Prev
    Next
    INDEX
    Explanations

    hot chocolate, dogs, tub, baths

    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
    utz
    -0.09
    hel
    -0.09
    enen
    -0.08
    Ŀ
    -0.08
    èĿĮ
    -0.08
    ç²Ĵ
    -0.08
    horn
    -0.08
    uster
    -0.08
    ably
    -0.08
    naire
    -0.08
    POSITIVE LOGITS
    ness
    0.14
    izontal
    0.11
    elligence
    0.10
    ÃŃsimo
    0.10
     mẽ
    0.10
    assium
    0.10
    ä¼ģ
    0.10
    burst
    0.10
    spots
    0.10
    çĦ¶æĺ¯
    0.10
    Activations Density 0.021%

    No Known Activations