© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21544
    Prev
    Next
    INDEX
    Explanations

    award winners and prizes

    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
    伶
    -0.09
    antis
    -0.09
    éģĺ
    -0.09
    pedo
    -0.09
    湫
    -0.08
    serializer
    -0.08
    èĥ±
    -0.08
    æĢ¥äºİ
    -0.08
    rove
    -0.08
    .getClassName
    -0.08
    POSITIVE LOGITS
    诺è´Ŀå°Ķ
    0.16
     Nobel
    0.15
     Pulitzer
    0.15
     award
    0.12
    èį£èİ·
    0.11
    èİ·å¾Ĺ
    0.11
    èİ·å¥ĸ
    0.10
    èµ¢å¾Ĺ
    0.10
     medal
    0.09
     Award
    0.09
    Activations Density 0.134%

    No Known Activations