© 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. 62219
    Prev
    Next
    INDEX
    Explanations

    determiners then specific nouns

    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
    æĵĤ
    -0.09
    oser
    -0.09
    åĵģå°Ŀ
    -0.09
    éħ¥
    -0.09
    è®¤çľŁèIJ½å®ŀ
    -0.08
     Lanc
    -0.08
    æĪĸ许æĺ¯
    -0.08
    3
    -0.08
    8
    -0.08
    4
    -0.08
    POSITIVE LOGITS
    cket
    0.09
    çĵľ
    0.09
    çĶ¨è½¦
    0.09
    è¿Ļå¥Ĺ
    0.09
    å°±å¤ŁäºĨ
    0.09
    Callable
    0.09
    agal
    0.09
    èĨĤ
    0.08
    è¿Ļ个游æĪı
    0.08
    èĢĮè¨Ģ
    0.08
    Activations Density 0.094%

    No Known Activations