© 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. 13917
    Prev
    Next
    INDEX
    Explanations

    nuclear, pharmaceutical, renal, phytotechnology

    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
    classname
    -0.19
     paul
    -0.19
    éĢIJ
    -0.19
    椰
    -0.19
     ClassName
    -0.19
    äºī
    -0.18
    æĪij们认为
    -0.18
    è¾ĩ
    -0.18
    触åĬ¨
    -0.18
    æ¨¡æł·
    -0.18
    POSITIVE LOGITS
    -Based
    0.30
    -based
    0.29
    -alone
    0.20
    æijĨ
    0.20
    绾
    0.20
    alone
    0.20
     Ramp
    0.20
    å·´åŁº
    0.19
    缸åĬ©
    0.19
    çķĮ第ä¸Ģ
    0.19
    Activations Density 1.374%

    No Known Activations