© 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. 7066
    Prev
    Next
    INDEX
    Explanations

    endure or withstand

    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
    ical
    -0.10
    iced
    -0.09
    one
    -0.09
    entr
    -0.09
    è¥ŀ
    -0.08
    uition
    -0.08
    writing
    -0.08
    ãģıãĤīãģĦ
    -0.08
    innacle
    -0.08
    icked
    -0.08
    POSITIVE LOGITS
    ably
    0.12
     Äijá»±ng
    0.11
    auc
    0.10
    orning
    0.10
    æľīä¸Ģ次
    0.10
    IBLE
    0.10
    ible
    0.10
    åĴĮæĶ¯æĮģ
    0.10
    ment
    0.09
    ingly
    0.09
    Activations Density 0.004%

    No Known Activations