© 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. 8655
    Prev
    Next
    INDEX
    Explanations

    streets and ordinal numbers

    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
    è«
    -0.09
    æѤç§į
    -0.09
    纰
    -0.09
     nug
    -0.09
    å¼ĢéĢļ
    -0.09
    çªĺ
    -0.09
    å¥ī
    -0.09
    eps
    -0.09
    å·¢
    -0.09
    æĸ°éĹ»ç½ij
    -0.09
    POSITIVE LOGITS
    æı½
    0.10
     Trim
    0.09
    åijĬè¯ī大家
    0.09
     اÙĦعÙħ
    0.08
     St
    0.08
    éĶ¡
    0.08
    趴
    0.08
     ImportError
    0.07
    赶
    0.07
    éĿŀ常éĩįè¦ģ
    0.07
    Activations Density 0.054%

    No Known Activations