© 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. 26140
    Prev
    Next
    INDEX
    Explanations

    to say the least

    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
    smith
    -0.09
    æ»Ĥ
    -0.09
    uela
    -0.09
    _ENCODE
    -0.09
    dsn
    -0.09
    endas
    -0.09
    çİ©åħ·
    -0.08
    änger
    -0.08
    BI
    -0.08
    urga
    -0.08
    POSITIVE LOGITS
    ãģķãĤī
    0.10
    ä¸įçĦ¶
    0.09
    idis
    0.09
    oric
    0.08
    æĿŀ
    0.08
    Į
    0.08
    éĨĭ
    0.08
    ä½Ĩå®ĥ
    0.08
    Jacob
    0.08
     pneum
    0.08
    Activations Density 0.028%

    No Known Activations