© 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. 30146
    Prev
    Next
    INDEX
    Explanations

    don't worry

    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
    ä¸įè§ģ
    -0.11
    åIJĦæł·
    -0.10
    è®´
    -0.10
    ×ķ×Ļ
    -0.10
    é«ĺå°Ķ
    -0.10
    usz
    -0.10
    beg
    -0.09
    ä¸įåĨįæĺ¯
    -0.09
    itzer
    -0.09
    å¦Ĥä½ķçľĭå¾ħ
    -0.09
    POSITIVE LOGITS
    æĶ¾å¿ĥ
    0.12
    fully
    0.11
    失
    0.09
    ä¸įçĶ¨æĭħå¿ĥ
    0.09
    หาย
    0.09
     Trou
    0.09
     worries
    0.08
    ÙĨÙĥ
    0.08
     Abed
    0.08
    åįı
    0.08
    Activations Density 0.010%

    No Known Activations