© 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. 14859
    Prev
    Next
    INDEX
    Explanations

    brand names linked to technology

    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
    ık
    -0.19
    æĹ¥æľ¬äºº
    -0.19
    ä¸įå°½
    -0.18
    draft
    -0.18
    onte
    -0.18
    è¿ŀè½½
    -0.18
     newsp
    -0.17
    rac
    -0.17
     constitution
    -0.17
    din
    -0.17
    POSITIVE LOGITS
    èĪ¹
    0.20
    å¤įæĿĤ
    0.19
    è°ħ
    0.18
    ลà¸ļ
    0.18
     watches
    0.18
    æĬ«éľ²
    0.18
     Watches
    0.18
    inkle
    0.18
    çĥŁèĬ±
    0.18
    éĿĻ
    0.17
    Activations Density 0.003%

    No Known Activations