© 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. 20692
    Prev
    Next
    INDEX
    Explanations

    US states

    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
    ä¸ŃåĽ½åĽ½éĻħ
    -0.10
    åĽ½éĻħå¸Ĥåľº
    -0.09
    èĮĶ
    -0.09
    们
    -0.09
    ä¼ļåijĺ
    -0.09
    å¸Ĥ人大
    -0.08
    ä¾Ĩèĩª
    -0.08
    æĿ¥èĩª
    -0.08
    åĮºç®¡å§Ķä¼ļ
    -0.08
     disturb
    -0.08
    POSITIVE LOGITS
    -born
    0.13
    åį«è§Ĩ
    0.12
    佬
    0.11
    ä¹ĥèĩ³
    0.10
    ç±į
    0.10
    æĹ¥æĬ¥è®°èĢħ
    0.10
    -based
    0.10
    çŃīåľ°
    0.10
    -made
    0.10
    é¦ĸå¯Į
    0.10
    Activations Density 0.132%

    No Known Activations