© 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. 2975
    Prev
    Next
    INDEX
    Explanations

    loss and extinction

    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
    婵
    -0.10
    çŃ¹å»º
    -0.09
    åįıåĬŀ
    -0.09
    ä¸Ģ个æľĪ
    -0.09
    asar
    -0.09
    embr
    -0.09
    ä¹IJéĺŁ
    -0.09
    -assets
    -0.09
    pons
    -0.09
    éĺ´
    -0.08
    POSITIVE LOGITS
    踪
    0.10
    æīĭå·¥
    0.09
    åıªåī©
    0.09
    åıªåī©ä¸ĭ
    0.09
    ç«¥
    0.09
    æ¶Ī失äºĨ
    0.09
    æ¯ģçģŃ
    0.09
    估计
    0.08
     ÑħозÑıйÑģÑĤв
    0.08
    oding
    0.08
    Activations Density 0.075%

    No Known Activations