© 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. 20989
    Prev
    Next
    INDEX
    Explanations

    linux distributions

    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
     Mou
    -0.08
    仪å¼ı
    -0.08
     fir
    -0.08
    åįĩ级æĶ¹éĢł
    -0.08
    客æ°Ķ
    -0.08
     coefficient
    -0.08
    æ°ijäºĭ
    -0.08
    èķ¨
    -0.08
    Tech
    -0.08
    èĭ±çī¹å°Ķ
    -0.08
    POSITIVE LOGITS
    ç±į
    0.10
    èĹī
    0.10
    icker
    0.10
    ickers
    0.10
    usta
    0.09
    主æĦı
    0.09
    oodle
    0.09
    ä½łçľĭ
    0.08
    秣
    0.08
    hower
    0.08
    Activations Density 0.112%

    No Known Activations