© 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. 22086
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative adjectives

    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
    顺
    -0.09
    ÑĪÑĥ
    -0.09
    sey
    -0.09
    SPORT
    -0.09
    æį©
    -0.09
    abbr
    -0.09
    alem
    -0.08
    çļĦè¯Ŀé¢ĺ
    -0.08
    ehler
    -0.08
    éłĨ
    -0.08
    POSITIVE LOGITS
    形容
    0.16
    修饰
    0.13
     adjective
    0.12
    æĿ¥å½¢å®¹
    0.11
    æııè¿°
    0.10
     describing
    0.10
     words
    0.09
    ad
    0.09
    åĴ¸
    0.09
    pac
    0.09
    Activations Density 0.073%

    No Known Activations