© 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. 24221
    Prev
    Next
    INDEX
    Explanations

    factors to, for, that, which, affecting

    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
    eries
    -0.10
    oire
    -0.09
    ipes
    -0.09
    igham
    -0.09
    noc
    -0.09
     Nes
    -0.09
    帮åĬ©ä¼ģä¸ļ
    -0.09
    åĩ«
    -0.09
    çŃ¾
    -0.08
    åĿıäºĭ
    -0.08
    POSITIVE LOGITS
    åĽłç´ł
    0.14
    (factor
    0.11
     factors
    0.11
    -factor
    0.10
    å½±åĵįåĬĽçļĦ
    0.09
    factor
    0.09
    èĢĥéĩı
    0.09
     Factors
    0.09
    积æŀģä½ľçĶ¨
    0.09
    ثر
    0.09
    Activations Density 0.087%

    No Known Activations