© 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. 36532
    Prev
    Next
    INDEX
    Explanations

    do you know?

    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
    Esc
    -0.10
    åľ¨æĪij
    -0.09
    arity
    -0.09
    çĽĬ
    -0.09
    jsonp
    -0.09
    _esc
    -0.08
    å¼Ī
    -0.08
    icket
    -0.08
    侦
    -0.08
    æݩ饰
    -0.08
    POSITIVE LOGITS
    åİŁèijĹ
    0.10
    è¿Ļä¹Īåģļ
    0.10
    åİŁæĿ¥çļĦ
    0.09
    äºĨåĩºæĿ¥
    0.09
    åĽłä¸ºä»ĸ们
    0.08
    ä¼¼çļĦ
    0.08
    å¦Ĥæľīä¾µæĿĥ
    0.08
    该æĢİä¹ĪåĬŀ
    0.08
    rog
    0.08
    äºĨä¸ĭæĿ¥
    0.08
    Activations Density 0.093%

    No Known Activations