© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 11695
    Prev
    Next
    INDEX
    Explanations

    shapes ending in 's' or 'disk' or 'sac' or 'rod'

    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»ıæµİåѦ
    -0.09
    èĪ«
    -0.09
    åĬ©çIJĨ
    -0.09
     viên
    -0.09
    çķĮçļĦ
    -0.09
    æĮĸ
    -0.08
    ook
    -0.08
    çѵ
    -0.08
    aurus
    -0.08
    å®ŀä¹ł
    -0.08
    POSITIVE LOGITS
    åĦ¿
    0.11
    çĬ¶
    0.10
    ngen
    0.09
    å¼ıçļĦ
    0.09
    å¼ı
    0.09
    çĭĢ
    0.09
     vul
    0.08
    èάçļĦ
    0.08
    лем
    0.08
    ÙĪØ·
    0.08
    Activations Density 0.274%

    No Known Activations