© 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. 62457
    Prev
    Next
    INDEX
    Explanations

    -ing ending words

    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
    fulness
    -0.10
    æĮģæľī人
    -0.10
    è¿ĩåī©
    -0.09
    æĥ®
    -0.09
    ascript
    -0.09
    edImage
    -0.09
    HING
    -0.09
    ierung
    -0.08
    .inspect
    -0.08
    æ·ŀ
    -0.08
    POSITIVE LOGITS
    ä»İå°ı
    0.09
    ailer
    0.09
    æĴŀ
    0.09
    rud
    0.09
    ongan
    0.08
    دس
    0.08
    讵
    0.08
    гоÑĢод
    0.08
    æľ¬èº«çļĦ
    0.08
    ä¹IJ趣
    0.08
    Activations Density 0.055%

    No Known Activations