© 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. 13698
    Prev
    Next
    INDEX
    Explanations

    computer programs or technical questions

    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
    iner
    -0.19
    รà¸ģ
    -0.19
    gre
    -0.19
    æĢ¯
    -0.19
    åľ®
    -0.18
    eba
    -0.18
    æµļ
    -0.18
     pillar
    -0.18
    èĹ»
    -0.18
     Pill
    -0.18
    POSITIVE LOGITS
    .jd
    0.21
    å¿ĥåºķ
    0.19
    _PAUSE
    0.19
    Layers
    0.19
    adian
    0.19
    éħŀ
    0.19
    ensch
    0.18
    ichel
    0.18
    模ç³Ĭ
    0.18
     пÑĢожива
    0.18
    Activations Density 0.006%

    No Known Activations