© 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. 60560
    Prev
    Next
    INDEX
    Explanations

    ordinal positions

    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
    è¿ĩåħ³
    -0.09
    çģ°
    -0.08
    å»ī
    -0.08
    pit
    -0.08
    äºĪ
    -0.08
    anny
    -0.08
    éĺ´
    -0.08
    atal
    -0.08
    篷
    -0.08
    æıī
    -0.08
    POSITIVE LOGITS
    第ä¸ĢåIJį
    0.13
    æİĴåIJį
    0.13
    å¥ĭ
    0.11
    rank
    0.10
     rank
    0.10
    æİĴè¡Į
    0.10
    _rank
    0.10
     ranked
    0.10
    .rank
    0.10
     rankings
    0.10
    Activations Density 0.083%

    No Known Activations