© 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. 12435
    Prev
    Next
    INDEX
    Explanations

    that is / that's

    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
    xab
    -0.10
    çĻ½æĸij
    -0.09
    łĢ
    -0.09
    abal
    -0.09
     however
    -0.09
    ç»ıéªĮ丰å¯Į
    -0.09
    çĦ¶èĢĮ
    -0.09
    erno
    -0.09
    åįģ大
    -0.09
    .expect
    -0.09
    POSITIVE LOGITS
    èµĽåIJİ
    0.08
    ä¸įéĢĤ
    0.08
    èĴº
    0.08
    лад
    0.08
    å°±å¤ŁäºĨ
    0.07
    tm
    0.07
     Nos
    0.07
    el
    0.07
    纰
    0.07
    tion
    0.07
    Activations Density 0.041%

    No Known Activations