© 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. 16614
    Prev
    Next
    INDEX
    Explanations

    names or places like wood, ridge, asset

    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
    åŀĽ
    -0.10
    æľ¬æĬ¥
    -0.10
    ç±³å°Ķ
    -0.09
    åĥı个
    -0.09
    agan
    -0.09
    å½»åºķ
    -0.09
    寨
    -0.08
    å½ĵäºĭ
    -0.08
    ä¸Ńåħ³æĿij
    -0.08
    æķĿ
    -0.08
    POSITIVE LOGITS
     Downing
    0.10
    raud
    0.09
    она
    0.09
    ÑĢÑİ
    0.09
    éĢłåŀĭ
    0.09
    çĺķ
    0.09
    éģ´éĢī
    0.08
     ê´Ģìĭ¬
    0.08
    esto
    0.08
    shal
    0.08
    Activations Density 0.002%

    No Known Activations