© 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. 47764
    Prev
    Next
    INDEX
    Explanations

    tear

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èħ¹éĥ¨
    -0.09
    ãģĹãģ¾ãģĨ
    -0.09
    ively
    -0.09
    atorial
    -0.09
     Ñĩа
    -0.09
    æīĭä¸ĭ
    -0.09
    urator
    -0.09
    åħ¶å®ĥ
    -0.08
    趺
    -0.08
    ertz
    -0.08
    POSITIVE LOGITS
    穹
    0.11
    å·´å·´
    0.10
    èĥ½æī¾åĪ°
    0.09
    ä¸Ŀä¸Ŀ
    0.09
    hardt
    0.09
    æµģ泪
    0.08
    ments
    0.08
    çĨ
    0.08
    们
    0.08
    áĢĦ
    0.08
    Activations Density 0.006%

    No Known Activations