© 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. 62788
    Prev
    Next
    INDEX
    Explanations

    internet domain paths

    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
     اÙĦسÙĨ
    -0.09
    让èĩªå·±
    -0.08
    éĶģå®ļ
    -0.08
    è¿ŀäºij
    -0.08
     ÑĤÑĥ
    -0.08
     aka
    -0.08
    å¼ĢåIJ¯
    -0.08
    2
    -0.08
    0
    -0.08
     Locked
    -0.08
    POSITIVE LOGITS
    clude
    0.10
    .FLAG
    0.10
    erv
    0.09
     ÑģамоÑģÑĤоÑı
    0.09
    .github
    0.09
    åĪ®
    0.09
    /win
    0.08
    éĤ¯
    0.08
    eness
    0.08
    .setStyleSheet
    0.08
    Activations Density 0.365%

    No Known Activations