© 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. 7577
    Prev
    Next
    INDEX
    Explanations

    punctuation for code/markup

    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
    ity
    -0.11
    ives
    -0.10
    {}",
    -0.09
    dit
    -0.09
    累累
    -0.09
    heimer
    -0.08
    -ish
    -0.08
    bole
    -0.08
    istance
    -0.08
    lah
    -0.08
    POSITIVE LOGITS
    [](
    0.16
    çĦ¶æĺ¯
    0.13
    !--
    0.10
    fully
    0.10
    amp
    0.09
    ful
    0.09
    aneously
    0.09
    ?!
    0.09
    âĺı
    0.09
    amous
    0.09
    Activations Density 0.118%

    No Known Activations