© 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. 57773
    Prev
    Next
    INDEX
    Explanations

    a followed by time units

    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
    éĢĤåIJĪ
    -0.09
    æĽ´éĢĤåIJĪ
    -0.08
    éĿłè°±
    -0.08
    ï¸
    -0.08
    åĴĮæĶ¯æĮģ
    -0.08
    çļĦå°±æĺ¯
    -0.08
    entially
    -0.08
    hall
    -0.07
    cial
    -0.07
    gio
    -0.07
    POSITIVE LOGITS
     Chatt
    0.10
    ä¸įå¾Ĺå·²
    0.10
    portun
    0.09
    绶
    0.09
    vertisement
    0.09
    身ä¸Ĭ
    0.09
    apesh
    0.09
    inki
    0.09
    èĿİ
    0.09
    éĥ½ä¸įçŁ¥éģĵ
    0.09
    Activations Density 0.090%

    No Known Activations