© 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. 38589
    Prev
    Next
    INDEX
    Explanations

    time since last update

    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
    kit
    -0.08
    åĦ¿
    -0.08
    swith
    -0.08
    ä¸īçĤ¹
    -0.08
    两çĤ¹
    -0.08
    æĪ´ä¸Ĭ
    -0.08
    æĺ¯ä¸įä¼ļ
    -0.08
    åĩĮæĻ¨
    -0.08
    责任å¿ĥ
    -0.07
    æĽ´å¼º
    -0.07
    POSITIVE LOGITS
    oses
    0.11
    ãģĦãĤį
    0.10
     многиÑħ
    0.09
    æĭĸ
    0.09
    umper
    0.09
    ä¼Ļ
    0.09
    TECT
    0.09
    .notifications
    0.09
    iali
    0.09
    åĶ±æŃĮ
    0.09
    Activations Density 0.044%

    No Known Activations