© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52660
    Prev
    Next
    INDEX
    Explanations

    awards or rankings

    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
    æĸ°çļĦä¸Ģ
    -0.11
    å»
    -0.10
    веÑģÑĤ
    -0.10
    ancock
    -0.09
    pling
    -0.09
    otros
    -0.09
    pla
    -0.09
    ean
    -0.08
    prises
    -0.08
    æĥº
    -0.08
    POSITIVE LOGITS
    ç»ıèIJ¥ç®¡çIJĨ
    0.10
    orest
    0.09
    unal
    0.09
    ลà¸Ń
    0.08
    æĪ¿è½¦
    0.08
    zano
    0.08
    äºĭåIJİ
    0.08
    ój
    0.08
    åĩ«
    0.08
     Maar
    0.08
    Activations Density 0.028%

    No Known Activations