© 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. 53558
    Prev
    Next
    INDEX
    Explanations

    historical periods or specific eras

    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
    åĪ©çī©
    -0.10
    ä¸İä¼Ĺä¸įåIJĮ
    -0.10
    çĶ·åıĭ
    -0.09
    çĶµåŃIJ产åĵģ
    -0.09
    _REGISTRY
    -0.09
     Lesb
    -0.09
    aroo
    -0.09
    è£ħè½½
    -0.09
    两级
    -0.09
    涯
    -0.09
    POSITIVE LOGITS
    æ°ijåĽ½
    0.13
    åı¤ä»£
    0.12
    è¿ij代
    0.12
    æĸ°ä¸ŃåĽ½
    0.11
    åı¤äºº
    0.11
    æ¸ħæľĿ
    0.11
    ä¸Ĭä¸ĸ纪
    0.11
     Nazi
    0.10
    åİĨåı²ä¸Ĭ
    0.10
    åİĨåı²æĤłä¹ħ
    0.10
    Activations Density 0.374%

    No Known Activations