© 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. 13116
    Prev
    Next
    INDEX
    Explanations

    technical nouns followed by description

    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
    åºŁè¯Ŀ
    -0.19
    åĵı
    -0.19
    wed
    -0.18
    ноÑģ
    -0.18
    .Components
    -0.18
    _MACHINE
    -0.18
    缼åħ¸
    -0.18
    oogle
    -0.18
     cach
    -0.17
    orate
    -0.17
    POSITIVE LOGITS
    åĴĮå¹³
    0.25
    éĿŀ常éĢĤåIJĪ
    0.25
    å°ijè§ģ
    0.23
    æĽ´éĢĤåIJĪ
    0.23
    æľĢéĢĤåIJĪ
    0.23
    æ³ķ
    0.20
    æīĢè°ĵ
    0.19
    ä¹Łå°±æĺ¯
    0.19
    leh
    0.19
    èĢĮéĿŀ
    0.18
    Activations Density 0.665%

    No Known Activations