© 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. 8463
    Prev
    Next
    INDEX
    Explanations

    names or initials

    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
     Malone
    -0.09
    akh
    -0.09
    .Manager
    -0.08
    ulin
    -0.08
     Surprise
    -0.08
     nj
    -0.08
    -Identifier
    -0.08
    UTO
    -0.08
    å¤ĩ
    -0.08
    æ¬
    -0.08
    POSITIVE LOGITS
    Ìģ
    0.10
    ernel
    0.10
    æı¡ä½ı
    0.10
    DMI
    0.09
    lectual
    0.09
    è°¥
    0.08
    åĬĽåѦ
    0.08
    urve
    0.08
    æľĢéĢĤåIJĪ
    0.08
    æįº
    0.08
    Activations Density 0.255%

    No Known Activations