© 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. 60763
    Prev
    Next
    INDEX
    Explanations

    debut album/collection/effort

    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
    人æ°ijæĶ¿åºľ
    -0.10
    оз
    -0.09
    ãĤ·ãĥ§
    -0.08
    hood
    -0.08
    ervo
    -0.08
    ways
    -0.08
    ãģıãĤĭ
    -0.08
    ÑģпоÑĢ
    -0.08
    èĪµ
    -0.08
    _builtin
    -0.08
    POSITIVE LOGITS
    ../../../
    0.13
    ä¸Ģæī¹
    0.11
    ä¸İåıijå±ķ
    0.11
    ä¹ĭä½ľ
    0.10
    åĴĮåıijå±ķ
    0.10
    ../../
    0.10
    tings
    0.10
    ary
    0.09
    stration
    0.09
    iful
    0.09
    Activations Density 0.012%

    No Known Activations