© 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. 26249
    Prev
    Next
    INDEX
    Explanations

    starting quotation marks

    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
    åĪģ
    -0.09
    INDER
    -0.09
    cio
    -0.08
    ä¸įå¿į
    -0.08
    رز
    -0.08
    åIJĥè¿ĩ
    -0.08
    èĭ¦
    -0.08
    ÑĢаг
    -0.08
    sofar
    -0.08
    å²Ń
    -0.08
    POSITIVE LOGITS
    è¿ĺ
    0.09
    ä¹ŁåĽłæѤ
    0.09
    ãĤ
    0.09
    untime
    0.08
     also
    0.08
    /inc
    0.08
    ãģªãĤĬ
    0.08
    apons
    0.08
    ä¹Łæ¯Ķè¾ĥ
    0.08
    ä¹Ł
    0.08
    Activations Density 0.063%

    No Known Activations