© 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. 26951
    Prev
    Next
    INDEX
    Explanations

    compelling case, films, mix, research, matchup, urge

    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
    稳
    -0.09
    yclopedia
    -0.08
    obe
    -0.08
    fra
    -0.08
    ients
    -0.08
    ovable
    -0.08
    ä¹ĺ
    -0.08
    isper
    -0.08
    åIJ¹
    -0.08
    pson
    -0.08
    POSITIVE LOGITS
    ly
    0.12
    çĥ
    0.12
    ency
    0.12
     nhất
    0.11
     liá»ĩt
    0.10
    åįģ足
    0.10
    诱æĥij
    0.10
     enough
    0.09
    ingly
    0.09
    ently
    0.09
    Activations Density 0.004%

    No Known Activations