© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38443
    Prev
    Next
    INDEX
    Explanations

    in a

    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
    enta
    -0.11
    ENTA
    -0.09
    stile
    -0.09
    áĢĬ
    -0.09
    erate
    -0.09
    åħ¢
    -0.08
     Hull
    -0.08
    æĵį
    -0.08
     Ventura
    -0.08
    plemented
    -0.08
    POSITIVE LOGITS
     ÙĦÙĦغا
    0.09
    ä¸įåłª
    0.09
    çĽ¼
    0.09
    æĿ¥åĽŀ
    0.09
    acz
    0.09
     ÙĪغÙĬر
    0.09
    ä¸Ķ
    0.09
    å¼Ģ端
    0.09
    atron
    0.09
    ADR
    0.08
    Activations Density 0.408%

    No Known Activations