© 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. 59355
    Prev
    Next
    INDEX
    Explanations

    circular reference or causal effects

    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
     piv
    -0.08
     bounty
    -0.08
     mim
    -0.08
    æijĩ
    -0.08
    çĻ½
    -0.07
    iso
    -0.07
    åįģåŃĹ
    -0.07
    AtIndex
    -0.07
    代表
    -0.07
    龸
    -0.07
    POSITIVE LOGITS
    åıįè¿ĩæĿ¥
    0.17
     itself
    0.12
    çĦ¶åIJİåĨį
    0.11
    lke
    0.11
    æĥº
    0.10
    æľ¬èº«
    0.10
    æľ¬èº«å°±æĺ¯
    0.10
    çļĦæĪIJéķ¿
    0.10
    æľ¬èº«çļĦ
    0.10
    è°ĥçļ®
    0.10
    Activations Density 0.115%

    No Known Activations