© 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. 29431
    Prev
    Next
    INDEX
    Explanations

    related to `collection`, `request`, `array`, `waveform`, `@`, `hello`

    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
    为客æĪ·
    -0.09
    åĬ¼
    -0.08
    ires
    -0.08
    å¸ĺ
    -0.08
    aw
    -0.08
    举éĥ¨
    -0.08
    åľ¨æĹ¥æľ¬
    -0.08
    è®©æĽ´å¤ļ
    -0.08
    å£ij
    -0.08
    ãĥ¼ãĥł
    -0.08
    POSITIVE LOGITS
    æĸ°åįİ
    0.09
    ople
    0.09
    ipop
    0.09
    æĮ¡
    0.08
    -fi
    0.08
    å¦Ħ
    0.08
    åºľ
    0.08
    outcome
    0.08
    æĤ¬
    0.08
    odyn
    0.08
    Activations Density 0.260%

    No Known Activations