© 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. 7312
    Prev
    Next
    INDEX
    Explanations

    python libraries common in code

    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
    =false
    -0.09
     instanceof
    -0.08
    =true
    -0.08
     Bourbon
    -0.08
    *Math
    -0.08
    æ¡¢
    -0.08
    onso
    -0.08
     eins
    -0.08
    =Math
    -0.08
    å¡«æĬ¥
    -0.08
    POSITIVE LOGITS
     pygame
    0.11
    (None
    0.11
    _py
    0.11
    pickle
    0.10
    .py
    0.10
    pygame
    0.10
    (Py
    0.10
     psycopg
    0.10
    _kwargs
    0.10
    None
    0.10
    Activations Density 1.043%

    No Known Activations