© 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. 17896
    Prev
    Next
    INDEX
    Explanations

    religious or memorial services

    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
    ernes
    -0.10
    .ZERO
    -0.09
    é»į
    -0.09
    à¸ģระà¸Ĺ
    -0.09
    /IP
    -0.09
    å¼ĢæĪ·
    -0.09
    åIJĥå¾Ĺ
    -0.09
     изд
    -0.09
    éĿ¢ä¸´çĿĢ
    -0.08
    ä»ķäºĭãĤĴ
    -0.08
    POSITIVE LOGITS
    ç»ĵæĿŁåIJİ
    0.09
    owns
    0.09
     halls
    0.09
    æĶ¸
    0.09
    绸
    0.09
     bowling
    0.09
    .GetObject
    0.08
    hall
    0.08
    ünk
    0.08
    nex
    0.08
    Activations Density 0.004%

    No Known Activations