© 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. 62313
    Prev
    Next
    INDEX
    Explanations

    focus on image

    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
    tester
    -0.09
    äºĭä¸ļéĥ¨
    -0.09
    rei
    -0.09
    飬
    -0.09
    æłª
    -0.09
    æ¸Ĭ
    -0.09
    å¥Ķæ³¢
    -0.08
    åĢĻ
    -0.08
    åı£æľį
    -0.08
    æ²Ļé¾Ļ
    -0.08
    POSITIVE LOGITS
    æ¸ħæĻ°
    0.16
    çĶ»åĥı
    0.13
    åĽ¾åĥı
    0.12
    çļĦåį°è±¡
    0.12
    çļĦ形象
    0.12
    模ç³Ĭ
    0.12
    çļĦçĶ»éĿ¢
    0.11
     images
    0.11
    å½±åĥı
    0.11
     image
    0.11
    Activations Density 0.138%

    No Known Activations