© 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. 57371
    Prev
    Next
    INDEX
    Explanations

    Jewish parenthood, Muslim women, Indonesian fair

    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
     Elem
    -0.09
    åĩłæ¬¡
    -0.08
    udu
    -0.08
    è¯ŀçĶŁ
    -0.08
    Scoped
    -0.08
    ures
    -0.08
    产éĶĢ
    -0.08
    thro
    -0.08
    æłª
    -0.08
    è¿ĪåIJij
    -0.08
    POSITIVE LOGITS
    oulder
    0.08
    ëĦ·
    0.08
    äºĮåŃĹ
    0.08
    MSN
    0.08
    éªĨ
    0.08
     Coron
    0.08
    å¾Ģå¤ĸ
    0.08
    renom
    0.08
    lung
    0.08
    olon
    0.08
    Activations Density 0.128%

    No Known Activations