© 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. 16469
    Prev
    Next
    INDEX
    Explanations

    small, short, low, thin

    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
    梨
    -0.21
    çļĦå¿ĥæĥħ
    -0.20
    Hat
    -0.20
    éĻĮçĶŁäºº
    -0.19
    _behavior
    -0.19
    ä¸įéĹ´æĸŃ
    -0.19
    æľīä¸įåIJĮçļĦ
    -0.19
    æĿ°åĩº
    -0.19
    OrFail
    -0.18
    æĺķ
    -0.18
    POSITIVE LOGITS
    ä¸į足以
    0.35
    åı¯æĢľ
    0.28
    æµħ
    0.27
    羸
    0.25
    ä¸įå¤Ł
    0.24
     (<
    0.23
    å¼±
    0.23
    ä¸į足
    0.23
    æ·º
    0.23
     compared
    0.22
    Activations Density 0.105%

    No Known Activations