© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51932
    Prev
    Next
    INDEX
    Explanations

    license

    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
    ses
    -0.13
    çļĦ人æĿ¥è¯´
    -0.10
    /from
    -0.09
    æľīä»·åĢ¼
    -0.09
     sake
    -0.09
    èĢĮè¨Ģ
    -0.09
    å°±è§īå¾Ĺ
    -0.09
    ç§įç§į
    -0.09
     behalf
    -0.09
    çݩ家æĿ¥è¯´
    -0.09
    POSITIVE LOGITS
    orem
    0.19
    oretical
    0.17
    oret
    0.14
     aim
    0.14
    odor
    0.12
    缮çļĦæĺ¯
    0.12
    è¿Ļä¹Łæĺ¯
    0.11
    åħ´è¶£
    0.11
    iming
    0.11
    æĮĩçļĦæĺ¯
    0.11
    Activations Density 0.526%

    No Known Activations