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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20763
    Prev
    Next
    INDEX
    Explanations

    sql field names

    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
    FER
    -0.09
     Som
    -0.08
     Cann
    -0.08
    æĮĩæĮ¥éĥ¨
    -0.08
    éĻ¶
    -0.08
     ÐľÐ¾Ñģков
    -0.08
    æ¯įå©´
    -0.08
    ga
    -0.08
    rians
    -0.08
    ä¸įæŃ»
    -0.08
    POSITIVE LOGITS
    varchar
    0.09
    _WS
    0.09
     varchar
    0.09
    ä½łè¯´
    0.08
     lÆ°u
    0.08
    bew
    0.08
    æ·Į
    0.08
    æĶ«
    0.08
    /helper
    0.08
     TableRow
    0.08
    Activations Density 0.989%

    No Known Activations