© 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. 4146
    Prev
    Next
    INDEX
    Explanations

    tedious, repetitive tasks

    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
    æ¬ł
    -0.09
    ToLocal
    -0.08
    åĪ«
    -0.08
    Editable
    -0.08
    rese
    -0.08
    rosse
    -0.08
    ogenesis
    -0.08
    æĽ´å¼º
    -0.08
    å¼ĢæĶ¾
    -0.08
    大èĥĨ
    -0.08
    POSITIVE LOGITS
    éĩįå¤į
    0.23
    æŀ¯çĩ¥
    0.22
     repetitive
    0.19
    æĹłèģĬ
    0.18
     tedious
    0.16
     repetition
    0.14
    åĬ³åĬ¨
    0.14
    åįķè°ĥ
    0.14
    ç¹ģçIJIJ
    0.14
    çIJIJ
    0.13
    Activations Density 0.145%

    No Known Activations