© 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. 7040
    Prev
    Next
    INDEX
    Explanations

    winner/winners

    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
    åѤåĦ¿
    -0.09
    workers
    -0.09
    åĬ¿åĬĽ
    -0.09
    æĹºçĽĽ
    -0.09
     Warfare
    -0.09
    èĩĥ
    -0.09
    agan
    -0.09
     Orig
    -0.08
    ä¸įä½ı
    -0.08
    ively
    -0.08
    POSITIVE LOGITS
    ouro
    0.10
    æĥķ
    0.10
    stral
    0.09
    -priced
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    ÙĤص
    0.08
    APPING
    0.08
    lä
    0.08
    chs
    0.08
    amil
    0.08
    Activations Density 0.008%

    No Known Activations