© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23912
    Prev
    Next
    INDEX
    Explanations

    US states or regions' abbreviations

    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
    ACY
    -0.09
    EX
    -0.09
    çĪ·
    -0.09
    åĽ½åĬ¡éĻ¢
    -0.09
    åºķä¸ĭ
    -0.08
    ofi
    -0.08
    çļĦåĪ°æĿ¥
    -0.08
     Shield
    -0.08
    佬
    -0.08
    æĺĨæĺİ
    -0.08
    POSITIVE LOGITS
    æĶ¾è¿ĩ
    0.10
    åĨľå®¶
    0.09
    ä¸Ģå¹´ä¸Ģ度
    0.09
    åĻ±
    0.09
    åįģåŃĹ
    0.08
    èĢģé¾Ħ
    0.08
    æĿ¡çº¦
    0.08
    lse
    0.08
    tml
    0.08
    å¾Īå¼Ģå¿ĥ
    0.08
    Activations Density 0.150%

    No Known Activations