© 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. 8952
    Prev
    Next
    INDEX
    Explanations

    Mickey Mouse, Mikey Garcia, Ricky

    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
    ilated
    -0.11
    à¹Ģà¸īà¸ŀาะ
    -0.10
    iliar
    -0.09
    elijke
    -0.09
    PLAIN
    -0.09
    wick
    -0.09
    åľ°ä¸Ń
    -0.09
    è¯Ŀ
    -0.09
    ayed
    -0.09
    quist
    -0.09
    POSITIVE LOGITS
    åħ´
    0.09
    Peripheral
    0.09
    ìĬ¨
    0.09
    SCO
    0.08
    æ¦ľ
    0.08
    sov
    0.08
    æ·¡åĮĸ
    0.08
    ôle
    0.08
    pile
    0.08
    bens
    0.08
    Activations Density 0.003%

    No Known Activations