© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36597
    Prev
    Next
    INDEX
    Explanations

    stereotype and archetype

    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
    uum
    -0.11
    egr
    -0.09
    oment
    -0.09
    ayo
    -0.09
    涤
    -0.08
    pedia
    -0.08
    对ä»ĸ们
    -0.08
    istant
    -0.08
    è¿Ļ两年
    -0.08
    rie
    -0.08
    POSITIVE LOGITS
    renc
    0.11
     Laur
    0.10
    æĹ¥æľ¬äºº
    0.09
    ivan
    0.09
    eway
    0.09
    饮éħĴ
    0.09
    裤
    0.09
    æĩ¦
    0.08
    °
    0.08
    Cha
    0.08
    Activations Density 0.006%

    No Known Activations