© 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. 48017
    Prev
    Next
    INDEX
    Explanations

    laboratory contexts

    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
    ulator
    -0.11
    лÑı
    -0.10
    inding
    -0.10
    åĶ¿
    -0.10
    该项
    -0.10
    ifiable
    -0.09
    èĢģ人家
    -0.09
    å¥Ī
    -0.09
    ened
    -0.09
    ley
    -0.09
    POSITIVE LOGITS
     lẽ
    0.09
    ToJson
    0.09
    жив
    0.09
    atl
    0.09
    æīİæł¹
    0.09
    annis
    0.08
    åĨħçļĦ
    0.08
    ÙĬست
    0.08
    eres
    0.08
    尽头
    0.08
    Activations Density 0.015%

    No Known Activations