© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51641
    Prev
    Next
    INDEX
    Explanations

    deep breath or relax

    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
    unal
    -0.10
    ä¸ļ
    -0.09
    躺çĿĢ
    -0.08
    ç¢Į
    -0.08
    éĩijåĪļ
    -0.08
    mens
    -0.08
    æĭĻ
    -0.08
    abal
    -0.08
    è°Ħ
    -0.08
    ä¸Ģç§į
    -0.08
    POSITIVE LOGITS
    åĬĽæ±Ĥ
    0.09
    æ¯ı次éĥ½
    0.09
    elm
    0.08
    åĬłéĩį
    0.08
    为人
    0.08
    æ¼Ĥ亮çļĦ
    0.08
    æľŁéĸĵ
    0.08
    IDI
    0.08
    æ§Ľ
    0.08
    æľŁéĹ´
    0.08
    Activations Density 0.007%

    No Known Activations