© 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. 54738
    Prev
    Next
    INDEX
    Explanations

    this,

    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
    iosity
    -0.10
    æĭ±
    -0.10
    詹
    -0.09
    åĽłèĢĮ
    -0.09
    .son
    -0.09
     undert
    -0.08
    obe
    -0.08
     Spir
    -0.08
     Tough
    -0.08
    è¿Ļä¸Ģ
    -0.08
    POSITIVE LOGITS
    ç§ĥ
    0.09
    æĿŁ
    0.09
    å¢Ļå£ģ
    0.09
    æĺ¯åĽłä¸º
    0.09
    æĺ¯éŁ©åĽ½
    0.09
    æĺ¯ä¸ºäºĨ
    0.09
    ä¹Łæĺ¯ä¸Ģç§į
    0.09
    æīįæĺ¯çľŁæŃ£
    0.09
    éĩįè¦ģæĦıä¹ī
    0.09
    å¥Ĥ
    0.09
    Activations Density 0.033%

    No Known Activations