© 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. 12866
    Prev
    Next
    INDEX
    Explanations

    Names followed by punctuation or sentence endings

    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
    æĴŃ
    -0.20
    对åѦçĶŁ
    -0.19
    ilar
    -0.18
    箬
    -0.18
    лиÑĨ
    -0.18
    大象
    -0.17
    ç¼±
    -0.17
    ë¹ħ
    -0.17
    inspace
    -0.17
    lug
    -0.17
    POSITIVE LOGITS
    âĦ¢
    0.19
     Syndrome
    0.18
    çļĦç§ĺå¯Ĩ
    0.18
    .googlecode
    0.18
     aka
    0.18
    è¡ĮåĪĹ
    0.18
    ä¹ĭ称
    0.17
    çļĦç«ŀäºī
    0.17
     Fil
    0.17
    banks
    0.17
    Activations Density 0.069%

    No Known Activations