© 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. 36277
    Prev
    Next
    INDEX
    Explanations

    glad you / to

    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
    éļ¾éģĵ
    -0.09
    acles
    -0.09
    强硬
    -0.09
    å¾Īéķ¿
    -0.09
    æĢª
    -0.08
    æ¬²æľĽ
    -0.08
    urge
    -0.08
    alled
    -0.08
    æľĢ强
    -0.08
    ãĤĤãģ¡
    -0.08
    POSITIVE LOGITS
    kj
    0.10
    âĸ¾
    0.09
    enty
    0.09
    åħįéĻ¤
    0.09
    åIJĦæĸ¹éĿ¢
    0.09
    kick
    0.09
    unic
    0.09
    ä¸įéĶĻ
    0.09
    è¹ĭ
    0.09
    entic
    0.09
    Activations Density 0.004%

    No Known Activations