© 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. 4377
    Prev
    Next
    INDEX
    Explanations

    redistributed

    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
    壮
    -0.09
    kok
    -0.08
    åĸĦ
    -0.08
    åĭĩæ°Ķ
    -0.08
    ä¸įåIJĪ
    -0.08
    èĭĶ
    -0.08
    ä¸įåĪ°
    -0.08
    GetComponent
    -0.08
    æ¶īæ¡Ī
    -0.08
    erialize
    -0.08
    POSITIVE LOGITS
    elly
    0.10
    æĢ§å¼º
    0.10
    èĥ¸æĢĢ
    0.10
    æľīå¤ļä¹Ī
    0.10
    é¢Ħæ¡Ī
    0.09
    èĬĿ
    0.09
    åľ°åĿª
    0.09
    ä¸įå¾Ĺå·²
    0.09
    ÙĪجب
    0.09
    åŀĵ
    0.08
    Activations Density 0.037%

    No Known Activations