© 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. 18159
    Prev
    Next
    INDEX
    Explanations

    this amount/type/manner/way

    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
    esty
    -0.12
    umont
    -0.11
    缺å¸Ń
    -0.10
    å¾Īéķ¿
    -0.09
    [__
    -0.09
    NullOr
    -0.09
    OLUMN
    -0.09
    â¾Ķ
    -0.09
    诸å¦Ĥ
    -0.09
    æĭ§
    -0.09
    POSITIVE LOGITS
     amount
    0.15
    级åĪ«çļĦ
    0.14
    æł·çļĦ
    0.14
     level
    0.13
     amounts
    0.12
     mức
    0.11
    amount
    0.11
     levels
    0.11
     sized
    0.11
    -sized
    0.11
    Activations Density 0.055%

    No Known Activations