© 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. 19151
    Prev
    Next
    INDEX
    Explanations

    company, founders, startups

    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
    ä¸įå¿į
    -0.09
    éħį
    -0.09
    港
    -0.08
    alia
    -0.08
    çľ·
    -0.08
    èĩªåѦ
    -0.08
    è¿Ľä¿®
    -0.08
    awning
    -0.08
    dup
    -0.07
     lap
    -0.07
    POSITIVE LOGITS
    åħ¬åı¸
    0.12
    åħ¬åı¸çļĦ
    0.12
    æł¸å¿ĥæĬĢæľ¯
    0.12
    æĺ¯ä¸Ģ家
    0.12
    åĪĽå§ĭ人
    0.12
     compañÃŃa
    0.11
     founders
    0.11
     company
    0.11
    è¿Ļ家åħ¬åı¸
    0.11
    èĿĮ
    0.11
    Activations Density 0.139%

    No Known Activations