© 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. 49680
    Prev
    Next
    INDEX
    Explanations

    anonymous or unnamed titles

    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
    è¿Ļä¸ªåľ°æĸ¹
    -0.09
    æĪĹ
    -0.09
    夷
    -0.09
    è¿Ļ个游æĪı
    -0.09
    èĽĽ
    -0.09
    æµ¼
    -0.09
    æ£ķ
    -0.09
    ÙĦغ
    -0.09
    åĩºåĵģ
    -0.09
    åĶł
    -0.09
    POSITIVE LOGITS
    åIJįåı«
    0.12
     unnamed
    0.10
    åĮ¿åIJį
    0.09
     anonymous
    0.09
    ern
    0.08
    anonymous
    0.08
    erv
    0.08
    åĨ¼
    0.08
     anonymously
    0.08
    åħħåĪĨåıijæĮ¥
    0.07
    Activations Density 0.232%

    No Known Activations