© 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. 20588
    Prev
    Next
    INDEX
    Explanations

    humanity and human beings

    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
     rid
    -0.10
    éĥ½çŁ¥éģĵ
    -0.09
    èĤ¢
    -0.08
    gles
    -0.08
    ture
    -0.08
    åĪĨåĮĸ
    -0.08
     pÅĤ
    -0.08
     ÑĢÑĥковод
    -0.08
    ä½ķ
    -0.08
    æŶ任
    -0.08
    POSITIVE LOGITS
    ä¸ĢéĿ¢
    0.11
    åħ³æĢĢ
    0.10
    åįģ足
    0.10
    åģĩæĹ¥
    0.10
    elay
    0.10
    æĺ¯éŁ©åĽ½
    0.09
    人æĢ§åĮĸ
    0.09
     дÑĥÑħ
    0.09
    请éĢīæĭ©
    0.09
    ingredient
    0.09
    Activations Density 0.019%

    No Known Activations