© 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. 37059
    Prev
    Next
    INDEX
    Explanations

    metastasis and extensions

    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
    åı¸
    -0.11
    æŃ»èĢħ
    -0.09
    zhou
    -0.09
    orman
    -0.09
    deen
    -0.08
     Geli
    -0.08
    ç°¸
    -0.08
     Kut
    -0.08
    à¸Ľà¸²à¸ģ
    -0.08
    å½¢åĬ¿
    -0.08
    POSITIVE LOGITS
    榨
    0.12
    è¡°èĢģ
    0.11
    夺
    0.11
    奪
    0.10
    ç²¾åįİ
    0.10
    夺åıĸ
    0.10
    èļķ
    0.09
    æİł
    0.09
    çīºçī²
    0.09
    æĮ¤åİĭ
    0.09
    Activations Density 0.091%

    No Known Activations