© 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. 24131
    Prev
    Next
    INDEX
    Explanations

    names ending in yer or man

    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
    éĩįå·¥
    -0.10
    uya
    -0.10
    èĵ¬åĭĥ
    -0.09
    erval
    -0.09
    å®ŀ践活åĬ¨
    -0.09
    allon
    -0.09
    å¼ĢèįĴ
    -0.09
    æľĽåİ»
    -0.09
    ä»İæѤ
    -0.09
    ublic
    -0.09
    POSITIVE LOGITS
    夫å¦ĩ
    0.11
    âĺİ
    0.09
     formerly
    0.09
    çŁ¥éģĵäºĨ
    0.08
     взÑıÑĤÑĮ
    0.08
     penc
    0.07
    ResponseStatus
    0.07
    æIJº
    0.07
     bart
    0.07
    .CONTENT
    0.07
    Activations Density 0.308%

    No Known Activations