© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15363
    Prev
    Next
    INDEX
    Explanations

    names ending in 'ene' or 'ane'

    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
    çѵ
    -0.22
    缮
    -0.19
    ä¸İä¼Ĺ
    -0.18
    æĪ¡
    -0.18
    èĨº
    -0.18
    errmsg
    -0.18
    æĺŃ
    -0.18
    _callbacks
    -0.18
    åIJĦåĮº
    -0.17
    ãģĿãģĨãģª
    -0.17
    POSITIVE LOGITS
    帮å¿Ļ
    0.28
    çļĦ帮åĬ©
    0.23
    åľ¨ä¸ĢæĹģ
    0.23
    帮åĬ©
    0.19
    _ORD
    0.19
    帮
    0.19
    çļĦ帮åĬ©ä¸ĭ
    0.19
    GRES
    0.18
    áºł
    0.18
    å§ij
    0.18
    Activations Density 0.044%

    No Known Activations