© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36001
    Prev
    Next
    INDEX
    Explanations

    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
     pháºŃn
    -0.12
    ìĤ¬íķŃ
    -0.11
     dõi
    -0.10
    ä¸įä¿¡
    -0.10
    íħį
    -0.10
    ãĤıãĤĬ
    -0.10
    -quarters
    -0.10
    åĸĬ
    -0.10
    htag
    -0.10
     Dwight
    -0.09
    POSITIVE LOGITS
    brush
    0.09
    rogen
    0.08
    ings
    0.08
    -song
    0.08
    forced
    0.08
    åī¯éĻ¢éķ¿
    0.08
    ะ
    0.08
    etty
    0.08
    tor
    0.08
    (Paint
    0.08
    Activations Density 0.020%

    No Known Activations