© 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. 58322
    Prev
    Next
    INDEX
    Explanations

    effort to

    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
    /or
    -0.11
    IMPLEMENT
    -0.09
    çļĦ大
    -0.08
    sequ
    -0.08
    RIES
    -0.08
     ÑįкÑģ
    -0.08
    èĮ¶
    -0.08
    åĽłèĢĮ
    -0.08
    plier
    -0.08
    ifold
    -0.08
    POSITIVE LOGITS
    æĹ©æĹ¥
    0.10
    èµĦ
    0.09
    éľĪ
    0.09
     Carpenter
    0.09
    åĩıå°ij
    0.08
    éģ¿å¼Ģ
    0.08
    æīĵ好
    0.08
    èĬĤèĥ½åĩıæİĴ
    0.08
    æ¯ķ
    0.08
    vironments
    0.08
    Activations Density 0.011%

    No Known Activations