© 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. 11684
    Prev
    Next
    INDEX
    Explanations

    wound and healing

    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
    åĻ©
    -0.18
    èľĥ
    -0.18
    纡
    -0.17
    é¹ī
    -0.17
    upe
    -0.16
    å¯ĨåĪĩåħ³æ³¨
    -0.16
    ãĤ¸ãĥ§ãĥ³
    -0.16
    éĽªèĬ±
    -0.15
     اÙĦزÙħÙĨ
    -0.15
     давно
    -0.15
    POSITIVE LOGITS
    ful
    0.21
    hip
    0.18
    ry
    0.17
    udu
    0.17
    нак
    0.17
    ãģ¾ãģ¾
    0.17
    edList
    0.17
    NING
    0.17
    pipe
    0.16
    ASTER
    0.16
    Activations Density 0.007%

    No Known Activations