© 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. 31739
    Prev
    Next
    INDEX
    Explanations

    side-by-side refrigerator

    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
    èľĪ
    -0.09
    æ¿ij
    -0.09
    ä¿Ŀéļľ
    -0.09
    esco
    -0.08
    holm
    -0.08
    æĶ«
    -0.08
    oser
    -0.08
     CAS
    -0.08
    奶èĮ¶
    -0.08
    alytics
    -0.08
    POSITIVE LOGITS
    æ´ŀ
    0.11
    éĵ®
    0.11
     Ży
    0.11
    éĥģ
    0.10
    èĽĨ
    0.10
    æī¿æĭħ
    0.09
    碴
    0.09
    arty
    0.09
     кÑĢÑĥ
    0.09
    迹象
    0.09
    Activations Density 0.052%

    No Known Activations