© 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. 16390
    Prev
    Next
    INDEX
    Explanations

    bonus tracks and documentaries

    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
    çīµ
    -0.20
    atre
    -0.19
     Evel
    -0.18
    ï¿¥
    -0.18
    aden
    -0.18
    estr
    -0.18
     SUS
    -0.17
    躯
    -0.17
     abstraction
    -0.17
    eterminate
    -0.17
    POSITIVE LOGITS
    丰å¯ĮçļĦ
    0.25
    äºĴåĬ¨
    0.23
    丰å¯Į
    0.23
    æ°Ķæ°Ľ
    0.21
    åĨħ容
    0.20
    访è°Ī
    0.20
    æłı
    0.20
    è±IJå¯Į
    0.20
    reich
    0.20
    åĮºåŁŁæĢ§
    0.19
    Activations Density 0.011%

    No Known Activations