© 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. 35570
    Prev
    Next
    INDEX
    Explanations

    improvement, update, change, evolution

    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
    å»ĭ
    -0.10
    gage
    -0.10
    anders
    -0.09
    çĺ¦
    -0.09
    Slim
    -0.09
    usercontent
    -0.09
    -widgets
    -0.09
    ÙĪÙĩ
    -0.09
    ocker
    -0.09
    .Uint
    -0.09
    POSITIVE LOGITS
    漫éķ¿çļĦ
    0.11
    æĿ¥çļĦ
    0.10
    è¿ĽæŃ¥
    0.10
    è°ģèĥ½
    0.09
    /extensions
    0.09
    .fi
    0.09
    ä¸ĭæĿ¥çļĦ
    0.09
    è°ģéĥ½
    0.09
    æĪij以为
    0.09
     oral
    0.09
    Activations Density 0.182%

    No Known Activations