© 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. 11016
    Prev
    Next
    INDEX
    Explanations

    "is a" followed by adjective

    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
    æľīæĽ´å¥½çļĦ
    -0.09
    æĽ·
    -0.08
    è·Ĺ
    -0.08
    缸åºĶçļĦ
    -0.08
    ToDate
    -0.08
     hob
    -0.08
     Anderson
    -0.08
    åĨľè´¸
    -0.08
     own
    -0.08
    éĹª
    -0.07
    POSITIVE LOGITS
    å¯Įè£ķ
    0.11
    unas
    0.09
    LER
    0.09
    èĢĥéªĮ
    0.09
    .mods
    0.09
    arded
    0.09
    åīįæīĢæľªæľī
    0.09
     ÑģлÑĥÑĩа
    0.08
    ekte
    0.08
    luent
    0.08
    Activations Density 0.030%

    No Known Activations