© 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. 63901
    Prev
    Next
    INDEX
    Explanations

    interchangeable parts and data formats

    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
    anto
    -0.10
    phin
    -0.09
    REM
    -0.09
    å¾Īé«ĺçļĦ
    -0.09
    ainty
    -0.09
    åĪ¨
    -0.08
    quir
    -0.08
    cci
    -0.08
    ãĥĺãĥ«
    -0.08
    rians
    -0.08
    POSITIVE LOGITS
    èĩªå¦Ĥ
    0.09
    äºĨå¤ļå°ij
    0.09
    uckle
    0.09
    oe
    0.09
    äºĨ大éĩıçļĦ
    0.09
    æį¢äºĨ
    0.09
    éĩijéĴ±
    0.08
    [$_
    0.08
    æĹłç¼Ŀ
    0.08
     interchangeable
    0.08
    Activations Density 0.010%

    No Known Activations