© 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. 60621
    Prev
    Next
    INDEX
    Explanations

    place names endings like shire, land, saxon, holstein

    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
    é¾ĻéŨ
    -0.11
    é¾Ł
    -0.09
    é¾Ľ
    -0.09
    æ»ļçIJĥ
    -0.09
    ocal
    -0.09
    iov
    -0.09
    çªł
    -0.09
    åĶ§
    -0.09
    aval
    -0.08
    åįģåł°
    -0.08
    POSITIVE LOGITS
    å¹³åİŁ
    0.10
    åĬ²
    0.09
    enha
    0.09
    è¿ĩåħ³
    0.09
    éģ½
    0.09
    è¸
    0.09
    è¾Ł
    0.08
    .mo
    0.08
    oland
    0.08
    æĤī
    0.08
    Activations Density 0.189%

    No Known Activations