© 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. 31520
    Prev
    Next
    INDEX
    Explanations

    Zuckerman / Zuccotti

    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
    ford
    -0.08
    寿
    -0.08
    aptor
    -0.08
    åijĺ
    -0.08
    åĵ¡
    -0.08
    hips
    -0.08
    aml
    -0.08
    è§ij
    -0.08
    angen
    -0.08
    ãģķãģĽãģ¦
    -0.08
    POSITIVE LOGITS
    èĮ«èĮ«
    0.09
    Brains
    0.09
    spi
    0.09
    rement
    0.09
    大家éĥ½åľ¨
    0.09
    å¾Ĺå¾Ī好
    0.09
    atal
    0.08
    inis
    0.08
    豪
    0.08
    èŀºä¸Ŀ
    0.08
    Activations Density 0.003%

    No Known Activations