© 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. 51915
    Prev
    Next
    INDEX
    Explanations

    lists joined by commas and 'and'

    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
    оÑĩнÑĭÑħ
    -0.08
    -ie
    -0.08
     Ñģли
    -0.08
    ä¼Ĭæĭī
    -0.08
    achers
    -0.08
    ffect
    -0.08
    è¿Ń
    -0.08
     даннÑĭм
    -0.07
    éģĵ士
    -0.07
     Baz
    -0.07
    POSITIVE LOGITS
    æĵĴ
    0.10
    éĥħ
    0.09
    CHandle
    0.09
    .Alignment
    0.09
     Bast
    0.09
    ç¥ĸåĽ½
    0.08
    æĪijåĸľæ¬¢
    0.08
    æ°¸è¿ľä¸įä¼ļ
    0.08
    .Generated
    0.08
    ä»Ģä¹Īäºĭæĥħ
    0.08
    Activations Density 0.037%

    No Known Activations