© 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. 34288
    Prev
    Next
    INDEX
    Explanations

    standard operating protocols

    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
    liness
    -0.10
    OperationException
    -0.10
    iable
    -0.09
    à¸ķรา
    -0.09
    红æĹĹ
    -0.09
    enn
    -0.09
    bestos
    -0.09
    baum
    -0.08
    å·§
    -0.08
    eparator
    -0.08
    POSITIVE LOGITS
    à¸ģาร
    0.11
    EDURE
    0.10
    èļ¤
    0.09
    ocols
    0.09
    estar
    0.08
    éħįæĸ¹
    0.08
    ä»įåľ¨
    0.08
    ìĤ¬íķŃ
    0.08
    chan
    0.08
    ´
    0.08
    Activations Density 0.021%

    No Known Activations