© 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. 24134
    Prev
    Next
    INDEX
    Explanations

    oxidative, oxes

    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
    atten
    -0.10
    alth
    -0.10
    åŀŃ
    -0.09
    feit
    -0.09
    atic
    -0.09
    .LayoutParams
    -0.09
     Torres
    -0.09
    pane
    -0.09
    agement
    -0.08
    atics
    -0.08
    POSITIVE LOGITS
    ç»
    0.10
    0.10
    ÑĪиÑĢ
    0.09
    æľĢå¿«
    0.09
    lox
    0.08
    涩
    0.08
    åīį线
    0.08
    /de
    0.08
    è¡·
    0.08
    cul
    0.08
    Activations Density 0.049%

    No Known Activations