© 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. 30591
    Prev
    Next
    INDEX
    Explanations

    sending something

    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
    è¦ģåģļåĪ°
    -0.09
    auc
    -0.09
    inges
    -0.08
    ä¸įçĦ¶
    -0.08
    ìļķ
    -0.08
    agan
    -0.08
    æĬ¥å¤į
    -0.08
    omore
    -0.08
    dependencies
    -0.08
    ãĤ¬ãĥ³
    -0.08
    POSITIVE LOGITS
    ä¸ŃåĮ»
    0.09
    /gpl
    0.09
    ECH
    0.09
    嵬
    0.09
    æĪijçľĭ
    0.09
     ÑĦоÑĢ
    0.09
    æ®·
    0.08
     Maurice
    0.08
    ISON
    0.08
    inand
    0.08
    Activations Density 0.017%

    No Known Activations