© 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. 21880
    Prev
    Next
    INDEX
    Explanations

    liver and associated conditions

    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
    çIJĨåıij
    -0.10
    ìĤ¬íķŃ
    -0.10
    ä¸Ģç³»åĪĹ
    -0.10
    æįĭ
    -0.10
    swith
    -0.09
    resses
    -0.09
    央
    -0.09
    emas
    -0.09
    ä¸ĭçļĦ
    -0.09
    åĸľåī§
    -0.08
    POSITIVE LOGITS
    ainen
    0.10
    zeit
    0.10
    estone
    0.09
    ologue
    0.09
    ieri
    0.09
    rias
    0.09
    ais
    0.08
    ä¸įåħĭ
    0.08
    زا
    0.08
    zug
    0.08
    Activations Density 0.028%

    No Known Activations