© 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. 39878
    Prev
    Next
    INDEX
    Explanations

    Field of the Invention, tumor detection

    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
    ish
    -0.09
    æĽ³
    -0.09
    åĽŀæĿ¥äºĨ
    -0.09
    éħ£
    -0.09
    itre
    -0.09
    éľ²å¤©
    -0.09
    åĸĦæĦı
    -0.09
    妯
    -0.08
    带åĽŀ
    -0.08
    yster
    -0.08
    POSITIVE LOGITS
    åĪ°è¾¾
    0.09
    ä½łè¦ģ
    0.08
     Ju
    0.08
     Doub
    0.08
    åħĪè¿Ľ
    0.08
     transf
    0.08
    åı¯è¾¾
    0.08
    åı¬
    0.08
    æīįè¡Į
    0.08
    æѧ
    0.08
    Activations Density 0.019%

    No Known Activations