© 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. 61994
    Prev
    Next
    INDEX
    Explanations

    access log visitor

    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
    ç»ı纬
    -0.10
    èĬĻèĵī
    -0.09
    éĤ£è¾¹
    -0.09
    åİļéĩį
    -0.09
    è¿Ļè¾¹
    -0.09
    .Schedule
    -0.09
    èĢ³è¾¹
    -0.09
    éĶ¦æłĩ
    -0.09
    bject
    -0.09
    .pick
    -0.09
    POSITIVE LOGITS
    æµı
    0.11
    仪表
    0.10
    .hits
    0.09
     visitors
    0.09
     pie
    0.09
    å¹ķåIJİ
    0.09
    èĿ´èĿ¶
    0.09
    visitor
    0.08
     Visitors
    0.08
    _visitor
    0.08
    Activations Density 0.175%

    No Known Activations