© 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. 4026
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers followed by comma

    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
    é²ľ
    -0.09
    åĴİ
    -0.08
    æĮ¯å¥ĭ
    -0.08
     Cra
    -0.08
    举æĸ¹è´¢å¯Į
    -0.08
    å®ŀçī©
    -0.08
    åıªæĺ¯ä¸ºäºĨ
    -0.08
    ä¹ı
    -0.08
    èĥ½æĬĬ
    -0.08
     tal
    -0.08
    POSITIVE LOGITS
    wart
    0.10
    ois
    0.09
    åħį
    0.09
    TECTED
    0.09
    hog
    0.09
    ãĥĭãĥ¥ãĥ¼ãĤ¹
    0.09
    patible
    0.08
    éĴ¿
    0.08
    ngr
    0.08
    زار
    0.08
    Activations Density 0.050%

    No Known Activations