© 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. 24216
    Prev
    Next
    INDEX
    Explanations

    start with an action

    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
    ly
    -0.09
    éĺ´
    -0.09
    LY
    -0.08
    å¯Łè§ī
    -0.08
    weis
    -0.08
    rip
    -0.08
    æĸ°åĮº
    -0.08
     Ly
    -0.08
    æĤĶ
    -0.08
    elli
    -0.07
    POSITIVE LOGITS
    AndUpdate
    0.10
    ä½łåľ¨
    0.10
    rophe
    0.09
    ä¸įè´Ł
    0.09
    代è¨Ģ
    0.09
    eturn
    0.09
    æĺ¨å¤©
    0.09
    è¯ķçĿĢ
    0.09
    代
    0.09
    çľĭçľĭ
    0.09
    Activations Density 0.075%

    No Known Activations