© 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. 14745
    Prev
    Next
    INDEX
    Explanations

    hockey related terms

    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
    istic
    -0.19
    åIJĨ
    -0.19
    енÑĮ
    -0.18
    itto
    -0.18
    ãĤĤãģĨ
    -0.17
    voy
    -0.16
     ngo
    -0.16
    icode
    -0.16
    OfWork
    -0.16
    åĩºå¤Ħ
    -0.16
    POSITIVE LOGITS
    rink
    0.19
    strap
    0.18
    erman
    0.18
    çĦ¶æĺ¯
    0.18
    ales
    0.17
    æ®ĩ
    0.17
    eer
    0.17
    å·¥ä¸ļ大åѦ
    0.17
    iest
    0.17
    è¡«
    0.16
    Activations Density 0.003%

    No Known Activations