© 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. 19993
    Prev
    Next
    INDEX
    Explanations

    richness and related qualities

    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
    æīª
    -0.10
    Aspect
    -0.10
    åĿļ飧
    -0.09
    éĤij
    -0.09
    bung
    -0.09
    è¯
    -0.09
    _BU
    -0.08
    æĶĢçĻ»
    -0.08
    é£İ
    -0.08
    çŃ·åŃIJ
    -0.08
    POSITIVE LOGITS
    丰å¯Į
    0.14
     richer
    0.13
     richest
    0.12
    æĸĩåĮĸåºķèķ´
    0.12
    rich
    0.12
     rich
    0.12
    丰å¯ĮçļĦ
    0.12
     richness
    0.12
    å¯Į
    0.11
    -rich
    0.11
    Activations Density 0.074%

    No Known Activations