© 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. 26859
    Prev
    Next
    INDEX
    Explanations

    oil painting and painters

    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
    éķĽ
    -0.10
    ạp
    -0.10
    è¾ľ
    -0.09
    èĿī
    -0.09
    bett
    -0.09
    cheduled
    -0.08
    ä¼´ä¾£
    -0.08
    åı¯è§Ĩ
    -0.08
    éĢļè¡Į
    -0.08
    åĬ³
    -0.08
    POSITIVE LOGITS
     paintings
    0.16
     painting
    0.15
    çĶ»å®¶
    0.15
    ç»ĺçĶ»
    0.14
    ä½ľåĵģ
    0.14
    çļĦä½ľåĵģ
    0.14
    æ²¹çĶ»
    0.13
     Painting
    0.12
    paint
    0.12
    çĶ»
    0.12
    Activations Density 0.270%

    No Known Activations