© 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. 3175
    Prev
    Next
    INDEX
    Explanations

    libraries, indexes, directories, galleries, calendars, glossaries

    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
    带åĬ¨
    -0.09
    bai
    -0.09
    èĪ¶
    -0.09
    ifik
    -0.08
    вен
    -0.08
    æIJºç¨ĭ
    -0.08
    isman
    -0.08
    ogo
    -0.08
    urbed
    -0.08
    _rq
    -0.08
    POSITIVE LOGITS
    åIJĦç±»
    0.11
    èĨĢ
    0.10
    è¿Ļä¸įæĺ¯
    0.09
    举
    0.09
    æŃĩ
    0.09
    çĶŁæ´»ä¸Ń
    0.09
    æ´½
    0.09
    åłª
    0.09
    åĦ¿å¥³
    0.08
    åĮĸåIJĪ
    0.08
    Activations Density 0.101%

    No Known Activations