© 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. 35107
    Prev
    Next
    INDEX
    Explanations

    heart conditions and disease

    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
    ruc
    -0.10
    管çIJĨæ°´å¹³
    -0.09
    å¼Ģ工建设
    -0.09
    åIJ¸çº³
    -0.09
    MAND
    -0.09
    .getField
    -0.09
    æīĵäºĨ
    -0.09
    éħįå¤ĩäºĨ
    -0.09
    管çIJĨä¸Ńå¿ĥ
    -0.09
    åľ£åľ°
    -0.09
    POSITIVE LOGITS
    ened
    0.11
    less
    0.11
    lessness
    0.10
    fulness
    0.10
    LESS
    0.09
    ness
    0.09
    lore
    0.09
    worm
    0.09
    bine
    0.08
    lessly
    0.08
    Activations Density 0.020%

    No Known Activations