© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24060
    Prev
    Next
    INDEX
    Explanations

    your [characteristic/need/item]

    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
    Negative Logits
    èĢģ人家
    -0.10
     маÑĤеÑĢиалÑĭ
    -0.10
    ä¸įçķĻ
    -0.09
    æīĵåĬ¨
    -0.09
    èIJ¥éĢłèī¯å¥½
    -0.09
    uali
    -0.09
    欺è¯Ī
    -0.09
    æ¼Ķä¹ł
    -0.09
    unes
    -0.09
    issen
    -0.09
    POSITIVE LOGITS
    åħ·ä½ĵæĥħåĨµ
    0.16
    è¿ĩå¾Ģ
    0.12
    å®ŀéĻħæĥħåĨµ
    0.12
    æīĢåľ¨
    0.11
    åħ´è¶£
    0.10
    æħ·æħ¨
    0.09
    æĢģ度
    0.09
    è¿Ľå±ķæĥħåĨµ
    0.09
     prior
    0.09
    èĥ½åIJ¦
    0.09
    Activations Density 0.024%

    No Known Activations