© 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. 9519
    Prev
    Next
    INDEX
    Explanations

    orthodontics

    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
    hetto
    -0.09
    丼
    -0.08
     UTIL
    -0.08
    éĻ¢
    -0.08
    ä¸įçŁ¥
    -0.08
    çĪ½
    -0.08
    /entity
    -0.08
    综åIJĪå¾ģ
    -0.07
    grav
    -0.07
    导
    -0.07
    POSITIVE LOGITS
    åĪĨå±Ģ
    0.09
    è£Ĥ
    0.09
    æłĸ
    0.09
    éļIJ身
    0.09
    .bmp
    0.09
    VK
    0.09
    éļ¶å±ŀäºİ
    0.09
     yuk
    0.08
    éģµå®Ī
    0.08
    oby
    0.08
    Activations Density 0.091%

    No Known Activations