© 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. 31062
    Prev
    Next
    INDEX
    Explanations

    country names and locations

    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
    çľīæ¯Ľ
    -0.10
    åıĹä¸įäºĨ
    -0.09
    rit
    -0.09
    澳大åĪ©äºļ
    -0.09
    澳洲
    -0.09
    zano
    -0.09
    APON
    -0.08
    éªij士
    -0.08
    åĿª
    -0.08
    ä¸įè´Ł
    -0.08
    POSITIVE LOGITS
    åĽ½æĥħ
    0.12
    æĢ»çIJĨ
    0.11
    ç®
    0.10
    ä¸į容æĺĵ
    0.10
    é¦ĸéĥ½
    0.09
    éĺħ
    0.09
    ä»ĩ
    0.09
    antz
    0.09
     desks
    0.08
     Collapse
    0.08
    Activations Density 0.238%

    No Known Activations