© 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. 14284
    Prev
    Next
    INDEX
    Explanations

    maze

    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
    ients
    -0.20
    s
    -0.19
    大家éĥ½åľ¨
    -0.18
    åŁºè°ĥ
    -0.18
    ness
    -0.18
    .setTo
    -0.18
    请大家
    -0.18
    åľ¨åºĬä¸Ĭ
    -0.17
     dụng
    -0.17
    tracked
    -0.16
    POSITIVE LOGITS
    buster
    0.20
    HOUSE
    0.18
     маÑĢÑĪÑĢÑĥÑĤ
    0.17
    emma
    0.17
    atical
    0.17
    +xml
    0.16
    house
    0.16
    éļ§
    0.16
    utton
    0.16
     maze
    0.16
    Activations Density 0.005%

    No Known Activations