© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 31300
    Prev
    Next
    INDEX
    Explanations

    Yankee Hill, Yankee Stadium, ize words

    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
    èĩ´åij½
    -0.09
    两ç§į
    -0.09
    .define
    -0.09
    è·
    -0.09
    å¸Ĥéķ¿
    -0.09
    å¸Ĥä¸Ńå¿ĥ
    -0.08
    ä¸Ģ举
    -0.08
    å¸ĤæĶ¿åºľ
    -0.08
    åīĬ
    -0.08
    海峡
    -0.08
    POSITIVE LOGITS
    ized
    0.10
    izers
    0.10
    佬
    0.10
    å¹¶éĿŀ
    0.10
    izing
    0.09
    ización
    0.09
    iz
    0.09
    ization
    0.09
    idge
    0.09
    izr
    0.08
    Activations Density 0.002%

    No Known Activations