© 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. 4360
    Prev
    Next
    INDEX
    Explanations

    dietary substances

    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
    æĭŁ
    -0.11
    说ä¸įåĩº
    -0.10
     reclaim
    -0.10
    èħĭ
    -0.10
    åIJĥçļĦ
    -0.09
    åīįæīĢæľªæľī
    -0.09
    æī¿è½½
    -0.08
    åīįæīĢæľª
    -0.08
    åĬŁ
    -0.08
    åĨįåĪ°
    -0.08
    POSITIVE LOGITS
     англи
    0.09
    è¿ľæĻ¯
    0.09
    oki
    0.08
    .inc
    0.08
    éĢĤéĩı
    0.08
    è¶Ĭé«ĺ
    0.08
    éĢĤ度
    0.08
    éĢĤå½ĵ
    0.08
    æľīåĬ©äºİ
    0.08
    å¯ĮåIJ«
    0.08
    Activations Density 0.038%

    No Known Activations