© 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. 1885
    Prev
    Next
    INDEX
    Explanations

    text search and matching

    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
    åħ³äºİæĪij们
    -0.10
    ãģ¨è¨Ģãģ£ãģ¦
    -0.09
    onest
    -0.08
    ä»Ģä¹Īä¸ľè¥¿
    -0.08
    ä¸įåİ»
    -0.08
    ãģ»ãģĨ
    -0.08
    大家ä¸Ģèµ·
    -0.08
    ä¹ĭåħ§å®¹
    -0.08
    é¹ī
    -0.08
    说å®ŀ
    -0.08
    POSITIVE LOGITS
    表述
    0.09
    earch
    0.09
    ague
    0.09
    æłı
    0.09
     match
    0.09
    åĩĨç¡®
    0.08
     search
    0.08
    èĩĨ
    0.08
     Sweat
    0.08
    amon
    0.08
    Activations Density 0.179%

    No Known Activations