© 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. 47407
    Prev
    Next
    INDEX
    Explanations

    Pablo, Picasso, Perez, Nolan

    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
    ances
    -0.10
    ties
    -0.10
    èĩ¾
    -0.09
    lessly
    -0.09
    ality
    -0.09
    ases
    -0.09
    shaw
    -0.09
    icine
    -0.09
    nut
    -0.08
    /from
    -0.08
    POSITIVE LOGITS
    ../../../
    0.10
    æģ¤
    0.10
    ãģıãĤĭ
    0.09
    è°ª
    0.09
    apor
    0.09
    窮
    0.09
    æł·çļĦ
    0.08
    ç©·
    0.08
    dır
    0.08
    ificate
    0.08
    Activations Density 0.006%

    No Known Activations