© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11177
    Prev
    Next
    INDEX
    Explanations

    barely

    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
    _CANNOT
    -0.19
    hammer
    -0.19
    RICT
    -0.19
    -overlay
    -0.19
    æ½ľåľ¨
    -0.18
    ç²¾ç»ĨåĮĸ
    -0.18
    大éĩıçļĦ
    -0.18
     strike
    -0.18
    ORY
    -0.17
    anut
    -0.17
    POSITIVE LOGITS
    çĶļèĩ³æĺ¯
    0.36
     überhaupt
    0.36
    çĶļèĩ³
    0.35
     вообÑīе
    0.34
     barely
    0.27
    çĶļèĩ³è¿ĺ
    0.27
     even
    0.27
    åĭī强
    0.26
    ä¸Ŀ
    0.25
    çĶļèĩ³è¿ŀ
    0.23
    Activations Density 0.071%

    No Known Activations