© 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. 57534
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    åī©ä¸ĭçļĦ
    -0.09
    iliar
    -0.08
    è¹Ģ
    -0.08
    âĢ¾
    -0.08
     اÙĦØ·
    -0.08
    ÙħÙħ
    -0.08
     stride
    -0.08
    æĿ¼
    -0.08
    éĹ²
    -0.08
    ษ
    -0.08
    POSITIVE LOGITS
    以便
    0.10
    éĢĤåºĶ
    0.10
    便äºİ
    0.10
    æķ´é¡¿
    0.10
    躲éģ¿
    0.09
    æ²ī浸
    0.09
     Infinity
    0.09
    åij¨æľ«
    0.09
    æ³Ľ
    0.09
    allow
    0.09
    Activations Density 0.064%

    No Known Activations