© 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. 14980
    Prev
    Next
    INDEX
    Explanations

    cell system, adhesion formation, fiber formation, layer regeneration, diaper routine, factor burden

    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
    UNC
    -0.20
    жа
    -0.19
    /legal
    -0.18
     Genius
    -0.18
    unch
    -0.17
    åģ¥åº·çļĦ
    -0.17
    izon
    -0.17
     Fellow
    -0.17
    пп
    -0.17
    isl
    -0.17
    POSITIVE LOGITS
    们çļĦ
    0.28
    们
    0.26
    æĢ»æķ°
    0.25
    ä¸Ģè§Ī
    0.20
    ëĵ¤ìĿĺ
    0.20
    ами
    0.20
    liste
    0.19
    太å¤ļ
    0.19
    太å¤ļäºĨ
    0.19
    åĢij
    0.19
    Activations Density 0.340%

    No Known Activations