© 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. 12833
    Prev
    Next
    INDEX
    Explanations

    commas followed by specific phrases

    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
    æľ¬æĿ¥å°±
    -0.21
    æīĢ以æĪij
    -0.20
     zwar
    -0.20
    ç»Īäºİ
    -0.20
    äºİæĺ¯
    -0.20
    åĽºçĦ¶
    -0.20
    æŀľçĦ¶
    -0.19
    mates
    -0.19
    å°±ä¼ļ
    -0.19
    ãģĿãģĹãģ¦
    -0.18
    POSITIVE LOGITS
    ä»įæľī
    0.24
    åį»
    0.23
    ä»įçĦ¶
    0.22
    åį´æĺ¯
    0.21
    åį´
    0.21
     nevertheless
    0.21
    è¿Ļåıªæĺ¯
    0.21
    iene
    0.20
    å®ŀéĻħæĥħåĨµ
    0.20
     ë¶Ī구íķĺê³ł
    0.20
    Activations Density 0.065%

    No Known Activations