© 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. 26486
    Prev
    Next
    INDEX
    Explanations

    in the presence of

    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
    å§Ĭ
    -0.10
    åł±åijĬ
    -0.10
    éªļæī°
    -0.09
    享åıĹ
    -0.09
     Pearce
    -0.09
    æĪIJåĬŁçļĦ
    -0.09
    issen
    -0.09
    ä¸īå¹´
    -0.08
    å§IJ妹
    -0.08
    æĬ¥åijĬ
    -0.08
    POSITIVE LOGITS
    å½ĵåľº
    0.12
    ä¼Ĺ人
    0.10
    ä¸ĭçıŃ
    0.09
     defer
    0.09
    åħ¶ä»ĸ人
    0.09
    .setView
    0.09
    çł
    0.09
    à¤ĸ
    0.08
    ä¸ĢæĹı
    0.08
    ä¼Ĺ
    0.08
    Activations Density 0.035%

    No Known Activations