© 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. 14651
    Prev
    Next
    INDEX
    Explanations

    -free, less

    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
    æĵĤ
    -0.20
     cena
    -0.18
     ControllerBase
    -0.17
    纵横
    -0.17
    arness
    -0.17
    cams
    -0.17
    ç«ŀæĬĢ
    -0.17
    à¸Łà¸²
    -0.17
     MainForm
    -0.17
    QA
    -0.17
    POSITIVE LOGITS
    -less
    0.32
    less
    0.32
    ä¸įäºĨ
    0.29
    -free
    0.26
    -Free
    0.25
    LESS
    0.23
    è¾ĥå°ij
    0.22
     nor
    0.22
    è¿ĺæĺ¯
    0.22
    lessness
    0.22
    Activations Density 0.440%

    No Known Activations