© 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. 32495
    Prev
    Next
    INDEX
    Explanations

    bulk or bulky

    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
    rup
    -0.10
    بط
    -0.09
    vro
    -0.09
    æĶ¾å¼Ģ
    -0.09
    iable
    -0.09
    ìŀ¥
    -0.08
    rek
    -0.08
    è·Ŀ离
    -0.08
    (hex
    -0.08
    Ark
    -0.08
    POSITIVE LOGITS
    èµ·æĿ¥äºĨ
    0.13
    èµ·æĿ¥
    0.11
    纱
    0.10
    ç»Ħç»ĩé¢Ĩ导
    0.10
    ç¢
    0.10
    缸åĬ©
    0.09
    -bodied
    0.09
    纩
    0.09
    ä¸ĢéĹª
    0.09
    éĿĵ
    0.09
    Activations Density 0.012%

    No Known Activations