© 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. 30290
    Prev
    Next
    INDEX
    Explanations

    ankle sprains and problems

    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
    nels
    -0.11
    fern
    -0.10
    å¿ĥ缮ä¸Ń
    -0.10
    nze
    -0.10
    äºijéĽĨ
    -0.09
    èĶ«
    -0.09
    nak
    -0.09
    åĪĩãĤĬ
    -0.09
    èį«
    -0.09
    æµģç¨ĭ
    -0.09
    POSITIVE LOGITS
     Simpson
    0.08
    çIJ°
    0.08
    伺
    0.08
    çģµæ´»æĢ§
    0.08
    undef
    0.08
    åģıå·®
    0.08
    åIJĸ
    0.07
    èĬĿ麻
    0.07
    adders
    0.07
    bone
    0.07
    Activations Density 0.031%

    No Known Activations