© 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. 3596
    Prev
    Next
    INDEX
    Explanations

    most recently, notably, commonly

    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åIJĹ
    -0.10
    æīŃ转
    -0.10
    åŃIJéĩĮ
    -0.10
    ⼦
    -0.10
    羣æŃ£åģļåĪ°
    -0.10
    .removeFrom
    -0.09
    ä¸į容æĺĵ
    -0.09
    çļĦéĤ£ç§į
    -0.09
    åĸĥ
    -0.09
    éĥ¨åĪĨ
    -0.09
    POSITIVE LOGITS
     recently
    0.10
     lately
    0.09
    å°¤
    0.09
    横
    0.09
    åIJİæĿ¥
    0.08
    è§Ĭ
    0.08
    è¿Ļåĩłå¹´
    0.08
     recent
    0.08
    导åIJij
    0.08
    æĮĩåIJij
    0.08
    Activations Density 0.050%

    No Known Activations