© 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. 20112
    Prev
    Next
    INDEX
    Explanations

    organizations and foundations

    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
    ç¼Ł
    -0.11
    桧
    -0.10
    éĺ¼
    -0.09
    ç¥ļ
    -0.09
    ä½ĵä¼ļåĪ°
    -0.09
    æ¸ĹéĢı
    -0.09
    æ»
    -0.08
    DEST
    -0.08
    èĢģå¸Ī们
    -0.08
    澧
    -0.08
    POSITIVE LOGITS
    æµij
    0.10
    ä¹ĭåŁİ
    0.09
    asta
    0.08
    çľ¼ä¸ĭ
    0.08
     Angelo
    0.08
    sa
    0.08
    çĽĪ
    0.08
    æ°Ļ
    0.08
    enger
    0.08
    å¿Ĵ
    0.08
    Activations Density 0.017%

    No Known Activations