© 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. 16523
    Prev
    Next
    INDEX
    Explanations

    films about giants

    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
    绾
    -0.20
    æĮĩçĿĢ
    -0.20
    åIJ¦
    -0.19
    该项
    -0.19
    ä»·
    -0.19
     Bands
    -0.18
    unicorn
    -0.18
    èĸ¨
    -0.18
    æĸ§
    -0.18
    USA
    -0.18
    POSITIVE LOGITS
    å½±çīĩ
    0.21
    æ²īé»ĺ
    0.20
     ìĹ
    0.20
     наг
    0.19
     filmed
    0.19
    èĿī
    0.19
    éķľå¤´
    0.19
    лÑij
    0.19
    纪å½ķçīĩ
    0.19
    çīĩ
    0.19
    Activations Density 0.045%

    No Known Activations