© 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. 23543
    Prev
    Next
    INDEX
    Explanations

    favicon and song files

    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
    ãģĹãģ¾ãģĨ
    -0.10
    AdapterFactory
    -0.10
    stead
    -0.09
    oad
    -0.09
    dana
    -0.09
    AAD
    -0.09
     ëĤĺëĬĶ
    -0.09
    AAC
    -0.08
    æĦıå¿Ĺ
    -0.08
    æļ´
    -0.08
    POSITIVE LOGITS
    å¦ĤæĦı
    0.09
    enha
    0.08
    ä¸ĸçķĮæĿ¯
    0.08
    è²Ķ
    0.08
     dụ
    0.08
    ement
    0.08
    åŀĤ
    0.08
    ape
    0.08
    ues
    0.08
    ä¸Ľä¹¦
    0.08
    Activations Density 0.003%

    No Known Activations