© 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. 64026
    Prev
    Next
    INDEX
    Explanations

    state of being or movement

    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
    åĽ´è§Ĥ
    -0.09
    ä¸ŃéĢĶ
    -0.08
    å¤Ķ
    -0.08
    oldem
    -0.08
    _handling
    -0.08
    ocard
    -0.08
    à¸ģา
    -0.08
    强åĬĽ
    -0.08
    é¢Ľ
    -0.08
     Ø£Ùħا
    -0.08
    POSITIVE LOGITS
    诸èijĽ
    0.09
    çĤ¸å¼¹
    0.09
    åħ¸èĮĥ
    0.09
    rä
    0.09
    æĦŁæŁĵèĢħ
    0.09
    åIJŀ
    0.08
    éļıæŶéļı
    0.08
    æľ¬èº«å°±
    0.08
    ç»ıå¼Ģ
    0.08
    嫱
    0.08
    Activations Density 0.036%

    No Known Activations