© 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. 7724
    Prev
    Next
    INDEX
    Explanations

    appears with date/time markers

    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
    计
    -0.08
    éĶIJ
    -0.08
    èĢģèĻİ
    -0.08
    åıµ
    -0.08
    åĴĤ
    -0.08
    梯
    -0.08
    æ®
    -0.08
    scal
    -0.08
    å¤ĩæ¡Ī
    -0.08
    GIN
    -0.08
    POSITIVE LOGITS
    ono
    0.10
    ä¸įå¿į
    0.09
    èĨı
    0.09
    /is
    0.08
    诸
    0.08
    idl
    0.08
    lose
    0.08
    DialogTitle
    0.08
    omin
    0.08
    æ´µ
    0.08
    Activations Density 0.022%

    No Known Activations