© 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. 33605
    Prev
    Next
    INDEX
    Explanations

    newline or carriage return characters

    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
    äºĶå®ĺ
    -0.10
    ä¸ĵ注
    -0.09
    æ¸ł
    -0.09
    ç¥ļ
    -0.09
     ÐŀÑĩ
    -0.09
    ç°ª
    -0.09
    sworth
    -0.09
    ä¸ĢæŃ¥æŃ¥
    -0.09
    è¿Ļä¸ĢåĪĩ
    -0.09
    åĩĨåħ¥
    -0.09
    POSITIVE LOGITS
    符
    0.11
    æį¢
    0.11
    æıĽ
    0.10
     lf
    0.09
     New
    0.09
    空
    0.09
    urus
    0.09
    éĩį
    0.09
     LF
    0.09
    è¿Ĥ
    0.09
    Activations Density 0.185%

    No Known Activations