© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35810
    Prev
    Next
    INDEX
    Explanations

    scene, table, mix, game, arena

    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
    æĸ¯é¡¿
    -0.09
     Ñģлова
    -0.09
    words
    -0.09
    åŀ¢
    -0.09
    çĵł
    -0.08
    çľł
    -0.08
    _HIDDEN
    -0.08
    spoken
    -0.08
    åĤ¾
    -0.08
    人们çļĦ
    -0.08
    POSITIVE LOGITS
    mites
    0.09
    ÑĢÑı
    0.09
    amp
    0.09
    tement
    0.08
    ãĥĥãĥĪ
    0.08
    ÑĢез
    0.08
    çĶŁçĶŁ
    0.08
    èģ¿
    0.08
    nuts
    0.08
    ä¸į妨
    0.08
    Activations Density 0.034%

    No Known Activations