© 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. 37646
    Prev
    Next
    INDEX
    Explanations

    progress or direction

    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
    ä¸įå½ĵ
    -0.10
    itted
    -0.09
    ophil
    -0.09
    tron
    -0.09
    راس
    -0.09
    å²Ľä¸Ĭ
    -0.09
    ä¸įä¹ı
    -0.09
    zed
    -0.09
    ä»İä¸Ń
    -0.09
    oyer
    -0.08
    POSITIVE LOGITS
    ppers
    0.10
    æŀģéĢŁ
    0.10
    æĽ´é«ĺçļĦ
    0.10
    /layouts
    0.09
    尽头
    0.09
    æĸ°çļĦä¸Ģå¹´
    0.09
    æĽ´å¥½çļĦ
    0.09
    ulti
    0.09
    缮æłĩ
    0.09
    gether
    0.08
    Activations Density 0.025%

    No Known Activations