© 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. 34181
    Prev
    Next
    INDEX
    Explanations

    King or Kings followed by names

    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
     же
    -0.10
    èķĥ
    -0.09
    天æīį
    -0.08
    èİ«æĸ¯
    -0.08
    åİ®
    -0.08
    ptic
    -0.08
    æij¸ç´¢
    -0.08
    ä¸ĥæĺŁ
    -0.08
    稣
    -0.08
    imated
    -0.08
    POSITIVE LOGITS
    fully
    0.10
    bury
    0.09
    berger
    0.09
    burg
    0.09
    mods
    0.08
    hear
    0.08
    PCS
    0.08
     обÑĢазом
    0.08
    ¬ģ
    0.08
    æ·ĩ
    0.08
    Activations Density 0.008%

    No Known Activations