© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15057
    Prev
    Next
    INDEX
    Explanations

    digital content and services

    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
    æĹ¢è¦ģ
    -0.20
    alent
    -0.19
    acent
    -0.19
    æĺ¨å¤©
    -0.19
    plen
    -0.19
    æĹ¢æĺ¯
    -0.19
    æĺ¨æĹ¥
    -0.19
     inspir
    -0.18
    çķĻä½ı
    -0.18
    çķĻå®Ī
    -0.18
    POSITIVE LOGITS
    礼åĮħ
    0.23
    使çĶ¨æĿĥ
    0.22
    çļĦåķĨåĵģ
    0.21
    ç»ĻæĤ¨
    0.21
    .unpack
    0.21
    ä¸ĸ家
    0.21
    å¥Ĺè£ħ
    0.20
    Assignable
    0.20
     guaranteed
    0.20
    éĻªä¼´
    0.20
    Activations Density 0.201%

    No Known Activations