© 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. 16056
    Prev
    Next
    INDEX
    Explanations

    Dallas Texas

    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
    çIJ¼
    -0.24
    åĬłå·ŀ
    -0.24
    éĤĽ
    -0.22
    浯
    -0.22
    æµ·åįĹçľģ
    -0.21
    ç§Ģ丽
    -0.21
    åĦĭ
    -0.21
    ç²Ĺ
    -0.21
     Castillo
    -0.20
    æ³Ķ
    -0.20
    POSITIVE LOGITS
     Lud
    0.26
    å¾IJå·ŀ
    0.25
    æ²Ľ
    0.23
    å³Ħ
    0.22
     lud
    0.22
     PCIe
    0.21
    ppe
    0.20
    Dat
    0.20
    éĺľ
    0.20
    dat
    0.19
    Activations Density 0.084%

    No Known Activations