© 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. 52504
    Prev
    Next
    INDEX
    Explanations

    dry ingredients

    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
    褶
    -0.09
    å«£
    -0.09
    çĭİ
    -0.09
    åĥı个
    -0.08
     concessions
    -0.08
    eways
    -0.08
    å¥ĭæĪĺ
    -0.08
    CellValue
    -0.08
    åIJĥå¾Ĺ
    -0.08
    å²ģ以ä¸ĭ
    -0.08
    POSITIVE LOGITS
    izable
    0.12
    ized
    0.10
    åĩ¿
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    IZED
    0.09
    ised
    0.09
    ities
    0.09
    zed
    0.08
    asu
    0.08
    æį§
    0.08
    Activations Density 0.009%

    No Known Activations