© 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. 11167
    Prev
    Next
    INDEX
    Explanations

    what is called or referred to

    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
    åĩŃä»Ģä¹Ī
    -0.21
    人éĢī
    -0.20
     Ä°z
    -0.19
    æľºæ²¹
    -0.19
    æľºç¥¨
    -0.19
    ãģ¨ãģĦãģĪãģ°
    -0.19
    nez
    -0.18
    çľĭçľĭ
    -0.18
    ặ
    -0.18
    ä»ĸåıĪ
    -0.18
    POSITIVE LOGITS
     "
    0.33
     “
    0.28
    “
    0.27
     '
    0.23
     «
    0.22
    "
    0.21
    å¥ij约
    0.21
    «
    0.19
     Mes
    0.19
    失
    0.19
    Activations Density 0.021%

    No Known Activations