© 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. 15862
    Prev
    Next
    INDEX
    Explanations

    as international players

    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
    åĪ°æľĢåIJİ
    -0.23
    åĪ°çİ°åľ¨
    -0.21
    æĪij们çİ°åľ¨
    -0.21
    lsi
    -0.20
    ä»Ĭãģ¯
    -0.19
    _now
    -0.19
    çŃīåĪ°
    -0.19
     now
    -0.19
    ä»ħ代表
    -0.19
    äºİæĺ¯
    -0.18
    POSITIVE LOGITS
    å°ļæľª
    0.21
    åıĪ被
    0.20
    mer
    0.20
    æīĵèµ¢
    0.20
    çĦ¦
    0.18
    è¿ĺ没æľī
    0.18
    åį³å°Ĩ
    0.18
    æŃ£åľ¨è¿Ľè¡Į
    0.18
    åħ¨åĽ½
    0.18
    asca
    0.18
    Activations Density 0.153%

    No Known Activations