© 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. 18757
    Prev
    Next
    INDEX
    Explanations

    information getting through

    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
    æľī人说
    -0.09
    å¾ĺ
    -0.09
    说çļĦè¯Ŀ
    -0.09
    æİī
    -0.09
    illi
    -0.08
    æİīäºĨ
    -0.08
    pd
    -0.08
    èIJĺ
    -0.08
     Müller
    -0.08
    apult
    -0.08
    POSITIVE LOGITS
    ฯ
    0.10
    ÙĨÙĪ
    0.09
    åĨ
    0.09
    åĪ©äºļ
    0.09
    æĽĻåħī
    0.09
    åĬ£
    0.09
    é»İæĺİ
    0.09
    ëĦ¤
    0.09
    åºŁå¼ĥ
    0.09
    çļĦä¸ĢéĿ¢
    0.09
    Activations Density 0.012%

    No Known Activations