© 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. 13713
    Prev
    Next
    INDEX
    Explanations

    separators and delimiters

    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
    åīįåĪĹ
    -0.18
    etro
    -0.18
    æĬ½åıĸ
    -0.17
    åīįä¸ī
    -0.17
    ä¸Ģæł·
    -0.17
    æĬ½
    -0.17
    ited
    -0.17
     cant
    -0.17
    www
    -0.17
    ä¸ĢåĪ»
    -0.17
    POSITIVE LOGITS
     minded
    0.19
    åĨľåī¯
    0.18
    Optimizer
    0.18
    ä¾Ŀæīĺ
    0.18
    éŀħ
    0.18
    个å¤ļ
    0.17
    argo
    0.17
    èľ©
    0.17
    WAR
    0.17
    åİĭè¿«
    0.16
    Activations Density 0.022%

    No Known Activations