© 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. 47604
    Prev
    Next
    INDEX
    Explanations

    Athens / Thebes

    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
    oundation
    -0.10
    ä¸Ģè¾ĪåŃIJ
    -0.09
    swith
    -0.09
    ĩ
    -0.09
    绣é¢Ĩ
    -0.09
    ç±Ģ
    -0.09
    们
    -0.09
    shaw
    -0.09
    é¢Ĩä¼ļ
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    POSITIVE LOGITS
    pheric
    0.12
    /or
    0.09
    áo
    0.09
    ÑĩиÑĤ
    0.09
    rese
    0.08
    ched
    0.08
    orte
    0.08
    çī¹æ®ĬæĥħåĨµ
    0.08
    soever
    0.08
    ensed
    0.08
    Activations Density 0.002%

    No Known Activations