© 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. 15078
    Prev
    Next
    INDEX
    Explanations

    salvation and spiritual deliverance

    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
    åĵģå¾·
    -0.21
    sr
    -0.20
    åĦ¿
    -0.18
    åĬŀæ¡Ī
    -0.18
    rade
    -0.17
     Dynam
    -0.17
    缸å½ĵ
    -0.17
    à¸Ļาà¸Ļ
    -0.17
    ulos
    -0.17
    MEA
    -0.17
    POSITIVE LOGITS
    cÃŃ
    0.21
    _LSB
    0.20
    itech
    0.19
     Crow
    0.18
     cdecl
    0.18
    fram
    0.18
    ä¹ĭè·¯
    0.17
    idd
    0.17
     Lutheran
    0.17
    .cf
    0.17
    Activations Density 0.005%

    No Known Activations