© 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. 35607
    Prev
    Next
    INDEX
    Explanations

    not only but also

    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
    çļĦ主è¦ģ
    -0.10
     addCriterion
    -0.10
    éķĿ
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    å·²ç»ıåľ¨
    -0.09
    æĢİä¹Ī说
    -0.09
    çIJª
    -0.09
    åıĹåĪ°å½±åĵį
    -0.09
    ä¸Ģ缴
    -0.08
    æĢİä¹Īçľĭ
    -0.08
    POSITIVE LOGITS
    åľ¨äºİ
    0.13
    äºİ
    0.12
    /or
    0.12
     LENG
    0.10
    åľ¨ä»ĸ
    0.08
    æĸ¼
    0.08
    phan
    0.08
    phans
    0.08
    iger
    0.08
     pada
    0.08
    Activations Density 0.376%

    No Known Activations