© 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. 35515
    Prev
    Next
    INDEX
    Explanations

    more than ever, today, now

    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
    é¦ĸæī¹
    -0.09
    裸
    -0.09
    è´¯
    -0.09
    åıĹå½±åĵį
    -0.09
    å°±æĺ¯è¦ģ
    -0.08
    æĮĽ
    -0.08
    ä¸Ģ缴
    -0.08
    æĤ£ä¸Ĭ
    -0.08
    ä¸Ģ缴åĪ°
    -0.08
     обÑĬ
    -0.08
    POSITIVE LOGITS
    åīįæīĢæľª
    0.15
    空åīį
    0.15
    åīįæīĢæľªæľī
    0.14
    æľīä¿¡å¿ĥ
    0.11
     unprecedented
    0.11
    è¦ģæ¯Ķ
    0.10
    çļĦæķ´ä½ĵ
    0.10
    åįģå¹´åīį
    0.10
    以åīį
    0.10
     compared
    0.10
    Activations Density 0.076%

    No Known Activations