© 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. 34846
    Prev
    Next
    INDEX
    Explanations

    abolitionist

    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
    ç®Ģ
    -0.11
    éªij士
    -0.09
    æ¯į
    -0.09
    åĽºåĮĸ
    -0.09
    è¿ĩå¾Ģ
    -0.08
    .png
    -0.08
    åħ¶ä»ĸçļĦ
    -0.08
    æĢ§å¼º
    -0.08
    ouis
    -0.08
     Hog
    -0.08
    POSITIVE LOGITS
    æĺ¥æĻļ
    0.09
     rad
    0.09
    é¼ĵåĬ±
    0.08
    arf
    0.08
    çĿĢæĢ¥
    0.08
    èĵĦ
    0.08
     Melania
    0.08
    æĺİçĻ½
    0.08
    çī¹æ´¾
    0.07
     Wendy
    0.07
    Activations Density 0.125%

    No Known Activations