© 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. 26949
    Prev
    Next
    INDEX
    Explanations

    workflow and routine

    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
    è·³è·ĥ
    -0.10
    论
    -0.09
    ntag
    -0.09
    éĢŁåº¦å¿«
    -0.09
    èĥ½åĬĽå¼º
    -0.09
    éĽĨä½ĵ
    -0.09
    è¯ĥ
    -0.09
    驺
    -0.09
    粪
    -0.08
    åĺīå¹´åįİ
    -0.08
    POSITIVE LOGITS
     routine
    0.14
    ä¾ĭè¡Į
    0.14
    æµģç¨ĭ
    0.13
     daily
    0.12
    è¿Ļå¥Ĺ
    0.12
     workflow
    0.11
    Routine
    0.11
     Routine
    0.11
    routine
    0.11
    æĵį
    0.11
    Activations Density 0.101%

    No Known Activations