© 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. 33718
    Prev
    Next
    INDEX
    Explanations

    to speak or say

    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
    好æľĭåıĭ
    -0.09
    éĽĦ
    -0.09
    uter
    -0.09
    诸å¦Ĥ
    -0.09
    arga
    -0.09
    mun
    -0.08
    ehler
    -0.08
    gles
    -0.08
    asz
    -0.08
    rog
    -0.08
    POSITIVE LOGITS
    åı¯ä»¥è¯´
    0.10
    rium
    0.10
    åı¯ä»¥è¯´æĺ¯
    0.10
    è¿Ļå°±
    0.10
    åľ°è¯´
    0.09
    羨
    0.09
    ä¸įé«ĺ
    0.09
     Whe
    0.08
    æľīä¸ĢçĤ¹
    0.08
    æĵģ
    0.08
    Activations Density 0.016%

    No Known Activations