© 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. 63937
    Prev
    Next
    INDEX
    Explanations

    Pacific followed by location or descriptor

    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
    é¼»åŃIJ
    -0.11
    è·µ
    -0.09
    kal
    -0.09
    ings
    -0.09
    seys
    -0.09
    åľ¨ä¸Ģèµ·
    -0.09
    velope
    -0.09
    ched
    -0.09
    velop
    -0.09
    ires
    -0.09
    POSITIVE LOGITS
    ç§įç§į
    0.12
    или
    0.11
    ALLY
    0.10
    ively
    0.10
     Downs
    0.09
    -facing
    0.09
    enne
    0.09
    иÑĤа
    0.09
    ا
    0.09
    ãĥ£
    0.09
    Activations Density 0.006%

    No Known Activations