© 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. 31298
    Prev
    Next
    INDEX
    Explanations

    walk-in closet

    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
    æĢ»ä¼ļ
    -0.10
    è¡Ģèħ¥
    -0.10
    ewire
    -0.10
    åĨ°åĨ·
    -0.10
    prd
    -0.09
    bih
    -0.09
    è°ĪæģĭçĪ±
    -0.09
    æļ´åĬĽ
    -0.09
    举起
    -0.09
    å¸Ĥåİ¿
    -0.08
    POSITIVE LOGITS
    omics
    0.10
    .effects
    0.09
    带æľī
    0.08
    effects
    0.08
    é¢Ĩ导å°ıç»Ħ
    0.08
    æĭĻ
    0.08
     ÑįÑĦÑĦ
    0.08
    ãģ«ãģ¤
    0.08
     Burl
    0.08
     orm
    0.08
    Activations Density 0.034%

    No Known Activations