© 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. 29790
    Prev
    Next
    INDEX
    Explanations

    military contexts and people

    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
    累累
    -0.12
    riv
    -0.10
    åľ¨è¿Ļç§į
    -0.09
    ãģ°ãģĭãĤĬ
    -0.09
    æ¯Ķäºļ
    -0.09
    icts
    -0.09
    ictions
    -0.09
    enstein
    -0.09
    èĢģ人家
    -0.08
     Dome
    -0.08
    POSITIVE LOGITS
    zed
    0.10
    -grade
    0.09
    yard
    0.09
    缸åħ³æĸ°éĹ»
    0.08
    -inspired
    0.08
    çĸıæķ£
    0.08
    หล
    0.08
    åĪ°æŶåĢĻ
    0.08
    交æİ¥
    0.08
    yyyy
    0.08
    Activations Density 0.013%

    No Known Activations