© 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. 50435
    Prev
    Next
    INDEX
    Explanations

    World of Warcraft

    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
    æĻ°
    -0.11
    راÙĨ
    -0.09
    å¤ĸ表
    -0.09
    ecal
    -0.09
    [email
    -0.09
    elly
    -0.08
    éĢĥè·ij
    -0.08
    åĨ°åĨ·
    -0.08
    ulum
    -0.08
    isu
    -0.08
    POSITIVE LOGITS
    è·¯æ¼Ķ
    0.09
    cw
    0.08
    ниÑĨÑĭ
    0.08
     rdr
    0.08
    .Nil
    0.08
     اÙĦÙħج
    0.08
    LIKE
    0.08
     Glory
    0.08
    å¹³åı°ä¸Ĭ
    0.08
    æµĬ
    0.08
    Activations Density 0.015%

    No Known Activations