© 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. 10530
    Prev
    Next
    INDEX
    Explanations

    properties and actions

    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
    ä¸ĬåѦ
    -0.10
    罩
    -0.09
    é¡ĺ
    -0.09
    æ¡Ī
    -0.09
    ainers
    -0.09
    æĦ¿
    -0.09
    ä¸Ĭå²Ĺ
    -0.09
    è¿ĩåħ³
    -0.08
    èĶļ
    -0.08
    æľįåĭĻæĪĸ
    -0.08
    POSITIVE LOGITS
    åħħå½ĵ
    0.10
    æĬĹæ°§åĮĸ
    0.10
    æĬĹèıĮ
    0.09
    åģ¥
    0.09
    æľĢéķ¿
    0.09
    anova
    0.09
    leck
    0.09
    温åĴĮ
    0.08
    çºłçº·
    0.08
    æĬĹæĹ¥
    0.08
    Activations Density 0.248%

    No Known Activations