© 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. 37803
    Prev
    Next
    INDEX
    Explanations

    change or switch

    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
    社ä¼ļåĮĸ
    -0.09
    tails
    -0.08
    ä»ĭåħ¥
    -0.08
    .Marker
    -0.08
    markup
    -0.08
    closure
    -0.08
     Bride
    -0.08
    å·§
    -0.08
    æ¶Ī失
    -0.08
    æĽ·
    -0.08
    POSITIVE LOGITS
    åıĺæĽ´
    0.13
    /change
    0.11
    åıĺåĬ¨
    0.11
    æĽ´æĶ¹
    0.10
     change
    0.10
    change
    0.09
     cambio
    0.09
     ë³Ģê²½
    0.09
    å±Ĭ
    0.09
    ä¸ŃéĢĶ
    0.09
    Activations Density 0.052%

    No Known Activations