© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11052
    Prev
    Next
    INDEX
    Explanations

    vicious cycle/loop

    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
    Negative Logits
    顺便
    -0.12
    çĵ¢
    -0.11
    acer
    -0.10
    æ²Ļæ¼ł
    -0.10
    éĥ¨åī¯
    -0.10
    åĶĨ
    -0.10
    æĻĤåĢĻ
    -0.10
    èļģ
    -0.09
    é£ĵ
    -0.09
    èµĸ以çĶŁåŃĺ
    -0.09
    POSITIVE LOGITS
    循çݯ
    0.18
     cycle
    0.15
     cycles
    0.14
    è½®åĽŀ
    0.14
    cycle
    0.14
    -cycle
    0.13
    Cycle
    0.12
     Cycle
    0.11
    cycles
    0.11
     ciclo
    0.11
    Activations Density 0.030%

    No Known Activations