© 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. 8541
    Prev
    Next
    INDEX
    Explanations

    in faith, this, its, his, heaven

    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
     Rena
    -0.10
    管çIJĨ模å¼ı
    -0.10
    客æĪ·æıIJä¾Ľ
    -0.10
    /msg
    -0.10
    è®·
    -0.09
    åıªä¸įè¿ĩæĺ¯
    -0.09
    leh
    -0.09
    æ¡£
    -0.09
     nominal
    -0.09
    ëĭĪëĭ¤
    -0.09
    POSITIVE LOGITS
    SSI
    0.09
    èĪĮ
    0.08
    è¿ĻçĤ¹
    0.08
    olle
    0.08
    åĪ«äººçļĦ
    0.08
    èģĨåIJ¬
    0.08
    åIJ¬çĿĢ
    0.08
    åIJijä¸Ĭ
    0.08
    ables
    0.08
     haz
    0.07
    Activations Density 0.032%

    No Known Activations