© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53209
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ledged
    -0.09
    é¾ĩ
    -0.09
    cken
    -0.08
    veled
    -0.08
    åľ¨æ¸¸æĪıä¸Ń
    -0.08
    ermann
    -0.08
    STA
    -0.08
    SHOT
    -0.08
    åĩĮ
    -0.08
    缺å¸Ń
    -0.08
    POSITIVE LOGITS
    èĸĦ
    0.12
     thin
    0.10
    gie
    0.09
    åģ·
    0.09
    æīģ
    0.09
    è¿ŀ
    0.09
    åħ¨éĿ¢æİ¨è¿Ľ
    0.08
     heir
    0.08
     overse
    0.08
    Thin
    0.08
    Activations Density 0.015%

    No Known Activations