© 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. 35811
    Prev
    Next
    INDEX
    Explanations

    ergonomics and related concepts

    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
    aron
    -0.10
    bur
    -0.09
    é£İäºij
    -0.08
    åħ¶ä»ĸ人
    -0.08
    æĽľ
    -0.08
    馥
    -0.08
    uki
    -0.08
    inch
    -0.08
    ndx
    -0.08
    oto
    -0.08
    POSITIVE LOGITS
    esus
    0.09
    æ¤ħ
    0.09
    ALLY
    0.09
    鸱
    0.09
    åįģ足
    0.09
    ValueCollection
    0.09
    æĪIJ
    0.09
    scopic
    0.08
    åı¦ä¸ĢåįĬ
    0.08
    èĨĤ
    0.08
    Activations Density 0.013%

    No Known Activations