© 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. 24282
    Prev
    Next
    INDEX
    Explanations

    familiar with

    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
    oby
    -0.09
    anism
    -0.09
    pile
    -0.09
    oblin
    -0.08
    åºŁ
    -0.08
    anke
    -0.08
    inning
    -0.08
    á»ĵn
    -0.08
    ferred
    -0.08
    ÑĨов
    -0.08
    POSITIVE LOGITS
    iliar
    0.13
    ity
    0.11
    ../../../
    0.11
    ä¸įäºĨ解
    0.10
    mente
    0.10
    ly
    0.10
     enough
    0.10
    åħĪè¿ĽæĬĢæľ¯
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    ç¨Ķ
    0.09
    Activations Density 0.014%

    No Known Activations