© 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. 22965
    Prev
    Next
    INDEX
    Explanations

    beauty and beautiful

    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
    æĭĪ
    -0.11
    å´Ń
    -0.09
    建åįİ
    -0.09
    aghan
    -0.09
    溥
    -0.08
    wang
    -0.08
    ÑĮев
    -0.08
    ä¸įæĸŃå¢ŀ强
    -0.08
    ond
    -0.08
    ç¾İå¾·
    -0.08
    POSITIVE LOGITS
    vard
    0.10
    rams
    0.10
    ä¹ĭå¤Ħ
    0.10
    ç¼Ľ
    0.10
    çĤ¸
    0.09
    eler
    0.09
    lice
    0.09
    æĪijçŁ¥éģĵ
    0.09
    conomy
    0.08
    ระ
    0.08
    Activations Density 0.014%

    No Known Activations