© 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. 60755
    Prev
    Next
    INDEX
    Explanations

    reissue, encore, rererereplay

    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
    ç¼
    -0.10
    éĻ¤æѤ
    -0.09
     пÑĢек
    -0.08
    éĺ¿å¯Įæ±Ĺ
    -0.08
    çļĦ人çī©
    -0.08
    以åħ¶
    -0.08
    è¿Ļæľ¬ä¹¦
    -0.08
    éĢĽ
    -0.08
    3
    -0.08
    åļ£
    -0.08
    POSITIVE LOGITS
    ä¸Ģéģį
    0.10
    castle
    0.09
    sett
    0.09
     Parkway
    0.09
    erre
    0.09
    çŁ³æ¦´
    0.09
    /ref
    0.09
     Petite
    0.08
    æĦŁäºº
    0.08
    æŧ
    0.08
    Activations Density 0.016%

    No Known Activations