© 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. 4109
    Prev
    Next
    INDEX
    Explanations

    Slate, Standard, Atlantic

    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
    è´¯
    -0.09
    æĺ¥å¤©
    -0.09
    tek
    -0.09
    ä»»ä½ķå½¢å¼ı
    -0.09
    ÄĻd
    -0.08
    -wow
    -0.08
    æ±½
    -0.08
    FromClass
    -0.08
    è®Ń
    -0.08
    è¤IJ
    -0.08
    POSITIVE LOGITS
    æ´ĭæ´ĭ
    0.09
    å¸®ä½ł
    0.09
    uzz
    0.09
    ä¸Ģç«Ļå¼ı
    0.09
    åħ¬çĶ¨
    0.09
     назнаÑĩен
    0.09
    SSF
    0.08
    åįİ缼
    0.08
    çļĦä¸ĢéĿ¢
    0.08
    CCR
    0.08
    Activations Density 0.051%

    No Known Activations