© 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. 2097
    Prev
    Next
    INDEX
    Explanations

    artists and actors who are not common

    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
    ä¸Ģæľ¬
    -0.10
    outu
    -0.10
    izzes
    -0.09
    大家ä¸Ģèµ·
    -0.09
    è±ļ
    -0.09
    بذ
    -0.09
     spons
    -0.09
    umbed
    -0.09
    utton
    -0.09
    odable
    -0.09
    POSITIVE LOGITS
     spare
    0.09
    æĪijæĺ¯
    0.08
    imin
    0.08
    ernet
    0.08
    åħĪè¿Ľ
    0.07
    æĸ¹åľĨ
    0.07
     impression
    0.07
    ç½ij讯
    0.07
    èªŀ
    0.07
    Lov
    0.07
    Activations Density 0.253%

    No Known Activations