© 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. 16138
    Prev
    Next
    INDEX
    Explanations

    wireless signal coverage

    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
    carbon
    -0.20
    åIJij社ä¼ļ
    -0.20
    æĸ¹å¼ıè¿Ľè¡Į
    -0.20
    ús
    -0.19
     pivot
    -0.19
     warmer
    -0.19
    arkan
    -0.19
    ickness
    -0.19
    _mirror
    -0.19
    _mass
    -0.19
    POSITIVE LOGITS
    è¦ĨçĽĸçİĩ
    0.33
     coverage
    0.25
     Coverage
    0.24
    å¹²æī°
    0.24
    ä¿¡åı·
    0.24
    æŃ»è§Ĵ
    0.24
     footprint
    0.24
    coverage
    0.23
    åŁºç«Ļ
    0.23
    è¦ĨçĽĸ
    0.23
    Activations Density 0.074%

    No Known Activations