© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19339
    Prev
    Next
    INDEX
    Explanations

    chewing on food and ruminants

    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
    å½Ģ
    -0.10
    ainted
    -0.09
    arih
    -0.09
    edReader
    -0.09
    rios
    -0.09
     رد
    -0.08
    å®ŀçĶ¨
    -0.08
    Disposition
    -0.08
    æĿIJ
    -0.08
    леÑĢ
    -0.08
    POSITIVE LOGITS
     chewing
    0.12
     chew
    0.11
    åĴ½
    0.10
    åĴĢ
    0.10
    ä¼łéĢĴ
    0.09
    æħ¢
    0.09
    гла
    0.09
    åļ¼
    0.09
    è¿ĻåIJį
    0.09
     Eck
    0.09
    Activations Density 0.029%

    No Known Activations