© 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. 13214
    Prev
    Next
    INDEX
    Explanations

    dosage and frequency

    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
    çī¹æľīçļĦ
    -0.20
    amas
    -0.20
     ghost
    -0.20
    滥
    -0.19
    迫使
    -0.19
    人å¿ĥ
    -0.19
    èĥĮä¸Ĭ
    -0.19
     material
    -0.18
    éģŃéģĩ
    -0.18
     path
    -0.18
    POSITIVE LOGITS
    çĿ¡åīį
    0.26
    æ¯ıæĹ¥
    0.25
    使çĶ¨èĢħæĪĸ
    0.22
    çĶŁäº§ä¼ģä¸ļ
    0.22
    æݨèįIJ
    0.22
    ìĶ©
    0.21
     минималÑĮ
    0.21
    éĢļçķħ
    0.21
    æĹ©æĻļ
    0.20
    _zone
    0.20
    Activations Density 0.013%

    No Known Activations