© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57684
    Prev
    Next
    INDEX
    Explanations

    the census

    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
    à¹Ģหà¸Ļ
    -0.11
    æī£
    -0.10
    å¼Ĥ
    -0.09
    éĵ¢
    -0.09
    å°ıæŶ
    -0.09
    éĵ
    -0.08
    _LCD
    -0.08
     Saul
    -0.08
    交éĻħ
    -0.08
    åħ±åĪĽ
    -0.08
    POSITIVE LOGITS
    æĻ®æŁ¥
    0.19
     census
    0.16
     Census
    0.16
    æĪ·åı£
    0.13
    æĪ·ç±į
    0.12
    å¦ĤæľŁ
    0.12
    人åı£
    0.11
     cá»Ń
    0.10
     наÑģелениÑı
    0.10
    åħ¥æĪ·
    0.09
    Activations Density 0.091%

    No Known Activations