© 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. 18056
    Prev
    Next
    INDEX
    Explanations

    works accompanying

    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
    å°ļ
    -0.09
    管çIJĨä¸Ńå¿ĥ
    -0.09
    æĮ½
    -0.09
    éĤ£åıª
    -0.09
    -pres
    -0.09
    èł¡
    -0.08
    çī¹å¾ģ
    -0.08
    quir
    -0.08
     pres
    -0.08
    oir
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īä¸ľè¥¿
    0.09
    éĩĮéĿ¢çļĦ
    0.09
    è¦Ĩ
    0.08
    åŀł
    0.08
    æĪIJæŀľ
    0.08
    utar
    0.08
    容纳
    0.08
    æĿ¥åĽŀ
    0.08
    æĬĹä½ĵ
    0.08
    inté
    0.08
    Activations Density 0.059%

    No Known Activations