© 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. 31161
    Prev
    Next
    INDEX
    Explanations

    Proper nouns, nationalities, locations, positions

    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
    æĪij以为
    -0.10
    主æķĻç»ĥ
    -0.09
    à¸ĩ
    -0.09
     dumb
    -0.09
    à¸Ĥà¸Ļาà¸Ķ
    -0.08
    èįij
    -0.08
     staring
    -0.08
    çļĩåIJİ
    -0.08
    èĢģå¦Ī
    -0.08
    Borders
    -0.08
    POSITIVE LOGITS
     grd
    0.08
    æĴŃ
    0.08
    便ä¼ļ
    0.08
    _aspect
    0.08
     بÙĥÙĦ
    0.08
     nale
    0.08
    -tra
    0.08
     alias
    0.08
    为代表
    0.08
     Kant
    0.08
    Activations Density 0.091%

    No Known Activations