© 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. 38788
    Prev
    Next
    INDEX
    Explanations

    Canada

    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
    anked
    -0.10
    ties
    -0.10
    ipsis
    -0.09
    ened
    -0.09
    idable
    -0.09
    å·´å·´
    -0.09
    ange
    -0.08
    iveness
    -0.08
    undy
    -0.08
    æĹ¶ä»£ä¸ŃåĽ½
    -0.08
    POSITIVE LOGITS
    oodle
    0.13
    -Muslim
    0.11
    oodles
    0.10
    /OR
    0.10
    ä¾
    0.10
    ģını
    0.10
    าว
    0.09
    å¤ļåľ°
    0.09
    ä¼ļåIJĮ
    0.09
    读åIJİ
    0.09
    Activations Density 0.027%

    No Known Activations