© 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. 26228
    Prev
    Next
    INDEX
    Explanations

    newsletter or digest

    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
    éĢ¸
    -0.09
    achs
    -0.09
    ç
    -0.09
    éĩĮç¨ĭç¢ij
    -0.08
    iete
    -0.08
    åŁ
    -0.08
     tre
    -0.08
     Tre
    -0.08
    èİĵ
    -0.08
    ault
    -0.08
    POSITIVE LOGITS
     newsletter
    0.14
     newsletters
    0.12
     Newsletter
    0.11
    newsletter
    0.11
    èĬľ
    0.11
    apos
    0.10
    ç½Ķ
    0.09
    Newsletter
    0.09
    Subscribe
    0.09
    éĢģè¾¾
    0.09
    Activations Density 0.075%

    No Known Activations