© 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. 1962
    Prev
    Next
    INDEX
    Explanations

    artery or aorta contraction

    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
    6
    -0.10
    ç¬Ķ
    -0.09
    Forms
    -0.09
    7
    -0.09
    3
    -0.09
    8
    -0.08
    4
    -0.08
    èĮ«
    -0.08
    ç´§
    -0.08
    å¿ij
    -0.08
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.10
    éĥ¨åī¯
    0.10
    庾
    0.09
    çģµéŃĤ
    0.09
    çī¹æĸ¯
    0.09
    æĸ¥
    0.09
    ä½ŀ
    0.09
    loadModel
    0.09
    ç³Ł
    0.08
     ник
    0.08
    Activations Density 0.654%

    No Known Activations