© 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. 54562
    Prev
    Next
    INDEX
    Explanations

    finding it

    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
    åı¯ä¸įæĺ¯
    -0.10
    åľ¨ä»ĸçļĦ
    -0.10
    äºij端
    -0.09
    æľīåIJįçļĦ
    -0.09
     пÑĢименÑı
    -0.09
    ä¿Ŀåį«
    -0.09
    avigator
    -0.09
     ноÑĩÑĮ
    -0.08
    åijĬè¯īæĪij们
    -0.08
    åĨĻçĿĢ
    -0.08
    POSITIVE LOGITS
    ÃľR
    0.09
    LER
    0.09
    UNE
    0.08
    OLER
    0.08
    etur
    0.08
    ä¹ĭè·¯
    0.08
    ulfilled
    0.08
    èĴĻ
    0.08
     ster
    0.08
    'aff
    0.08
    Activations Density 0.021%

    No Known Activations