© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27977
    Prev
    Next
    INDEX
    Explanations

    landmark decisions and articles

    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
    Not in Any Lists

    No Comments

    Negative Logits
    hound
    -0.10
    venge
    -0.10
    walk
    -0.10
    cess
    -0.10
    atron
    -0.10
    atura
    -0.09
    ราà¸ĩ
    -0.09
    andel
    -0.09
    ãĤıãĤĮ
    -0.09
    abble
    -0.09
    POSITIVE LOGITS
    ing
    0.10
    ãģ¥
    0.10
    人士
    0.10
    çļĦåĪ°æĿ¥
    0.09
    å½ĸ
    0.09
    é¢ı
    0.09
    们
    0.09
    çİ«
    0.09
    çĪª
    0.09
    建çŃijæĿIJæĸĻ
    0.08
    Activations Density 0.008%

    No Known Activations