© 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. 13298
    Prev
    Next
    INDEX
    Explanations

    performance and installation

    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
    å¸ľ
    -0.20
    åIJĪ计
    -0.20
    页
    -0.18
    æĸ°æł¼å±Ģ
    -0.18
    CEPT
    -0.18
    dale
    -0.18
    åķĨçĶ¨
    -0.17
    ills
    -0.17
     Sammy
    -0.17
    ä¸Ģ大æī¹
    -0.17
    POSITIVE LOGITS
    èīºæľ¯å®¶
    0.21
     live
    0.21
    æĢ§å¼º
    0.20
    表æ¼Ķ
    0.20
    eph
    0.19
     ephem
    0.18
    .uml
    0.18
    .extensions
    0.18
     perd
    0.18
    æĦı大
    0.17
    Activations Density 0.010%

    No Known Activations