© 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. 29751
    Prev
    Next
    INDEX
    Explanations

    Piper, Eugenia, orILLA

    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
    æĥħ人èĬĤ
    -0.09
    æĬĺ
    -0.09
    atha
    -0.09
    åŀ®
    -0.09
    ê³±
    -0.09
    åŃĺæ´»
    -0.09
    迤
    -0.09
     appendString
    -0.09
     läng
    -0.08
    ially
    -0.08
    POSITIVE LOGITS
    ä»ģ
    0.09
    åŃij
    0.09
    ivas
    0.08
    èĥ¡åŃIJ
    0.08
     revers
    0.08
    éĤªæģ¶
    0.08
    æī¿æİ¥
    0.08
    å¿Ĵ
    0.08
    lien
    0.08
    å¸ĤåľºçĽij管
    0.08
    Activations Density 0.018%

    No Known Activations