© 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. 63932
    Prev
    Next
    INDEX
    Explanations

    exclamation marks

    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
    å°±å¾Ī
    -0.09
    çł´
    -0.08
    øy
    -0.08
    atif
    -0.08
    ä¹Łå°±
    -0.07
    mage
    -0.07
     ÑĢÑĭ
    -0.07
     Said
    -0.07
     semif
    -0.07
    atter
    -0.07
    POSITIVE LOGITS
    æĭ
    0.10
    ä¸įå¦Ĥ
    0.09
    楣
    0.09
    çīĮ
    0.09
    éĺħ读åħ¨æĸĩ
    0.08
    驹
    0.08
    PAD
    0.08
    æļ¹
    0.08
    anton
    0.08
    cms
    0.08
    Activations Density 0.054%

    No Known Activations