© 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. 62374
    Prev
    Next
    INDEX
    Explanations

    mk followed by errors or file extensions

    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
    als
    -0.11
    å¸ĥå°Ķ
    -0.09
    åŀł
    -0.09
    abilities
    -0.09
    oral
    -0.09
    产åѦ
    -0.08
    printer
    -0.08
    ALS
    -0.08
    est
    -0.08
    .Net
    -0.08
    POSITIVE LOGITS
    Ŀ
    0.09
    essler
    0.09
    ÑģÑĤÑĥп
    0.09
    .localization
    0.09
    orrent
    0.08
    aton
    0.08
    æijĦ
    0.08
    æĬ¢æķij
    0.08
    zos
    0.08
    åģľçķĻ
    0.08
    Activations Density 0.017%

    No Known Activations