© 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. 17903
    Prev
    Next
    INDEX
    Explanations

    route or routes

    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¿Ļ件
    -0.11
    âĮIJ
    -0.10
    棺
    -0.10
    è¿Ļæĸ¹éĿ¢
    -0.10
    åĿıäºĨ
    -0.10
    ardin
    -0.09
    ä¸Ģ件
    -0.09
    æĥ³æī¾
    -0.09
    ä¸Ģåı°
    -0.09
    Qualified
    -0.09
    POSITIVE LOGITS
    路线
    0.23
     routes
    0.20
     route
    0.20
    è·¯å¾Ħ
    0.18
     path
    0.17
     paths
    0.16
    线路
    0.16
    route
    0.16
    轨迹
    0.15
    .routes
    0.14
    Activations Density 0.095%

    No Known Activations