© 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. 35482
    Prev
    Next
    INDEX
    Explanations

    things, features, or confusing aspects

    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
    æĤ£æľī
    -0.10
    åĽĽç§į
    -0.09
    åĩłç§į
    -0.09
    éĢĭ
    -0.09
    æĬĬè¿Ļ个
    -0.09
    è¿Ļæł·ä¸Ģ个
    -0.09
    两ç§į
    -0.09
    áŀł
    -0.08
    ä¸īç§į
    -0.08
    dera
    -0.08
    POSITIVE LOGITS
    æĺ¯æĪij
    0.11
    没è§ģè¿ĩ
    0.09
    lg
    0.09
    æĺ¯æĪijçļĦ
    0.09
    åİŁæĿ¥æĺ¯
    0.09
    apons
    0.09
    NIC
    0.09
    lig
    0.09
    çĶļèĩ³æĺ¯
    0.09
    ëĪĦ
    0.08
    Activations Density 0.210%

    No Known Activations