© 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. 26840
    Prev
    Next
    INDEX
    Explanations

    Mandarin, python

    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
     mẽ
    -0.09
    磼
    -0.09
    ev
    -0.09
    POR
    -0.09
    å¿ĸ
    -0.08
    åĻ¨æĿIJ
    -0.08
    æĭ¢
    -0.08
    ëĭĪëĭ¤
    -0.08
     lud
    -0.08
    arb
    -0.08
    POSITIVE LOGITS
    à¸Ľà¸¥
    0.09
    ../../../
    0.09
    акÑģ
    0.09
    onica
    0.09
    ALS
    0.09
    æ¹¾
    0.09
    odes
    0.08
    usty
    0.08
    åħµåĽ¢
    0.08
    ctions
    0.08
    Activations Density 0.008%

    No Known Activations