© 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. 48369
    Prev
    Next
    INDEX
    Explanations

    inventory, stock, storage

    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
    è·¯çģ¯
    -0.10
    MAS
    -0.09
    è´¿
    -0.08
    æĸ½èĤ¥
    -0.08
    éĢĢå¸Ĥ
    -0.08
    kip
    -0.08
    uls
    -0.08
    大大å°ıå°ı
    -0.08
    fee
    -0.08
    chl
    -0.08
    POSITIVE LOGITS
    åĤ¨å¤ĩ
    0.19
    åºĵåŃĺ
    0.15
    åĤ¨
    0.15
    åĦ²
    0.15
    åºĵ
    0.15
    åĤ¨åŃĺ
    0.14
    åŃĺåĤ¨
    0.14
    è´®
    0.12
    庫
    0.12
    åĤ¨èĥ½
    0.11
    Activations Density 0.037%

    No Known Activations