© 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. 40149
    Prev
    Next
    INDEX
    Explanations

    how much

    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
    Harness
    -0.11
    庸
    -0.10
    CHAN
    -0.09
    editable
    -0.09
    ichel
    -0.08
     Went
    -0.08
     Harness
    -0.08
     dangling
    -0.08
    è¿IJ
    -0.08
    urma
    -0.08
    POSITIVE LOGITS
    éĶ²
    0.10
    ä¸İæŶ
    0.10
    éĿ¢çĽ®
    0.09
    ä¹Łä¸įåı¯èĥ½
    0.09
    解æĶ¾æĢĿæĥ³
    0.09
    outed
    0.09
    ilos
    0.09
    çijĢ
    0.09
    oted
    0.09
    çĭ¬ä¸Ģ
    0.09
    Activations Density 0.161%

    No Known Activations