© 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. 9707
    Prev
    Next
    INDEX
    Explanations

    Indian states and regions

    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
    èµĦåĬ©
    -0.10
    ä½¼
    -0.09
    uti
    -0.09
    误导
    -0.09
    éĢĿ
    -0.09
    .choice
    -0.09
    çµķ
    -0.09
    erah
    -0.08
    åĬª
    -0.08
    SSI
    -0.08
    POSITIVE LOGITS
    å¸ĪèĮĥ大åѦ
    0.11
    人æ°ij
    0.09
    ä¸ĢæĿ¯
    0.09
    _lite
    0.09
    beck
    0.09
    sek
    0.08
    åį«è§Ĩ
    0.08
    lis
    0.08
    ä¸įåĪĨ
    0.08
    ä¸Ģçķª
    0.08
    Activations Density 0.038%

    No Known Activations