© 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. 11445
    Prev
    Next
    INDEX
    Explanations

    positive qualities

    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
    tit
    -0.09
    ç°Ł
    -0.09
     ÐłÐ°
    -0.08
    ng
    -0.08
    ä¸Ģå®ļä¼ļ
    -0.08
    çĤ¹äºĨ
    -0.08
    æ´¼
    -0.08
    gid
    -0.08
    æŀķ
    -0.08
    çŃ¹èµĦ
    -0.08
    POSITIVE LOGITS
    æļĸ
    0.09
    æĢĶ
    0.09
    .hasOwnProperty
    0.09
    åĩºè·¯
    0.09
    æļ§
    0.08
    è¿ĻéĩĮæĺ¯
    0.08
    å¤ļåľ°
    0.08
    æĺİæĺİ
    0.08
     dyn
    0.08
    漫éķ¿
    0.08
    Activations Density 0.112%

    No Known Activations