© 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. 16751
    Prev
    Next
    INDEX
    Explanations

    on or its equivalents

    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
    ect
    -0.09
    æĬķéĻį
    -0.09
    èĩ£
    -0.09
    æĺİçŁ¥
    -0.09
    pta
    -0.09
    ptom
    -0.08
    _SCL
    -0.08
    pt
    -0.08
    ç¼ĺåĪĨ
    -0.08
    ahan
    -0.08
    POSITIVE LOGITS
    ampo
    0.08
    PRI
    0.08
    åŁºç¡Ģä¸Ĭ
    0.08
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.08
     panc
    0.08
    erez
    0.08
    åı¯æĮģç»Ń
    0.08
    ðŁijĨ
    0.08
     imposs
    0.08
    ä¸ĢæŶ
    0.08
    Activations Density 0.153%

    No Known Activations