© 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. 1356
    Prev
    Next
    INDEX
    Explanations

    decreasing size or diameter

    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
    .Lib
    -0.09
    liches
    -0.09
    èħ¾
    -0.09
    人工
    -0.09
     Dominion
    -0.09
     Baron
    -0.08
    æĭĨ
    -0.08
    åįģä¸ĩ
    -0.08
    _barrier
    -0.08
     Artificial
    -0.08
    POSITIVE LOGITS
    åĿ¡
    0.12
    ä¸Ģç¬Ķ
    0.11
    yne
    0.10
    åĽ¾å½¢
    0.10
    ä¸Ģå¤Ħ
    0.09
    дей
    0.09
    è¶ĬæĿ¥è¶Ĭå°ij
    0.09
    åĪ°æľĢåIJİ
    0.09
    alse
    0.09
    çĤ¹åįĬ
    0.09
    Activations Density 0.083%

    No Known Activations