© 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. 13945
    Prev
    Next
    INDEX
    Explanations

    years and dates

    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
    éĢı
    -0.20
    pan
    -0.19
    owitz
    -0.19
    оваÑĤÑĮ
    -0.18
     loose
    -0.18
    пан
    -0.18
    éĤ£æł·
    -0.18
    hta
    -0.18
    dess
    -0.17
    èĿĻ
    -0.17
    POSITIVE LOGITS
    èµĽåŃ£
    0.24
    æĺ¥åŃ£
    0.23
     Ñģез
    0.22
    åŃ£åIJİ
    0.21
    äºİæĺ¯æĪij
    0.20
    åŃ£
    0.20
    å¾ģ
    0.20
    iming
    0.20
    ä¼ĺéĢī
    0.19
    åŃ£èĬĤ
    0.19
    Activations Density 0.054%

    No Known Activations