© 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. 51019
    Prev
    Next
    INDEX
    Explanations

    burst into tears or collapse

    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
    踽
    -0.09
    é¬ĵ
    -0.08
    åĴ§
    -0.08
    ä»ĭåħ¥
    -0.08
    صÙĦØ©
    -0.08
     Manus
    -0.08
    ạp
    -0.08
    è¯ķçĿĢ
    -0.08
    åĽ½åºĨ
    -0.08
    tl
    -0.08
    POSITIVE LOGITS
    æĭ¾
    0.11
    å¯¹æľªæĿ¥
    0.09
    è¶ĬæĿ¥è¶Ĭ
    0.09
    ÑģÑĥд
    0.09
    衽
    0.09
    acier
    0.09
    èĭij
    0.09
    飦
    0.08
    æĸ°ä¸Ģè½®
    0.08
    èģĮä¸ļ
    0.08
    Activations Density 0.010%

    No Known Activations