© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17000
    Prev
    Next
    INDEX
    Explanations

    parts and features of structures and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    çĭ¸
    -0.21
    满
    -0.20
    elder
    -0.20
    orners
    -0.19
     or
    -0.19
     cán
    -0.19
    å¿į
    -0.19
    ktop
    -0.18
    mpp
    -0.18
    åįĥéĩĮ
    -0.18
    POSITIVE LOGITS
    侧
    0.21
    çªĿ
    0.20
     location
    0.20
    ä¸Ģæľ¬ä¹¦
    0.20
     обÑıзаÑĤелÑĮ
    0.19
    ä½įç½®
    0.19
    è´¿
    0.19
    ogo
    0.19
     holder
    0.19
    ABI
    0.19
    Activations Density 0.111%

    No Known Activations