© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7207
    Prev
    Next
    INDEX
    Explanations

    dentures, contact lenses, prosthetics

    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
    ä»»
    -0.10
    éħŀ
    -0.09
    æ°´æµģ
    -0.08
    encent
    -0.08
    çłŃ
    -0.08
    NoSuch
    -0.08
    çļĦçłĶåıij
    -0.08
     Listing
    -0.08
    æ°´æºIJ
    -0.08
     distr
    -0.08
    POSITIVE LOGITS
    éģĹ
    0.12
    佩æĪ´
    0.10
    èĨĿçĽĸ
    0.10
    éģº
    0.10
    mas
    0.09
    _mas
    0.09
    æĭ¿ä¸ĭ
    0.09
    æĪijåıªæĺ¯
    0.09
    è£½ä½ľ
    0.09
    sole
    0.08
    Activations Density 0.147%

    No Known Activations