© 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. 11235
    Prev
    Next
    INDEX
    Explanations

    car and other nouns

    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
    oller
    -0.19
    ç¥ĵ
    -0.19
    å¾Ĺå¤ļ
    -0.19
    è¿Ļ个è¯į
    -0.19
     Chung
    -0.19
    é»ij客
    -0.18
    æķijåĬ©
    -0.18
    igned
    -0.17
    _notes
    -0.17
    çĶº
    -0.17
    POSITIVE LOGITS
    太å¤ļäºĨ
    0.22
    楼
    0.20
    åħ¶å®ĥéĹ®é¢ĺ
    0.20
    Ä±ÅŁÄ±
    0.20
    çĹķ迹
    0.20
    è·¡
    0.19
     Syndrome
    0.18
    æĥ¶
    0.18
     syndrome
    0.18
    ä¼ļè®©ä½ł
    0.17
    Activations Density 0.530%

    No Known Activations