© 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. 12380
    Prev
    Next
    INDEX
    Explanations

    .xml files and xml tag names

    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
    ably
    -0.19
    rier
    -0.19
    ниÑĨа
    -0.18
    iveness
    -0.18
    ches
    -0.18
    iate
    -0.18
    quo
    -0.18
    uple
    -0.18
    iful
    -0.17
    epar
    -0.17
    POSITIVE LOGITS
    åĪ¶åĵģ
    0.21
    rpc
    0.20
    åĮĸçļĦ
    0.19
    æ±ģ
    0.17
     BIND
    0.16
    PullParser
    0.16
    ä»ħä¾ĽåıĤèĢĥ
    0.16
    itet
    0.15
    tod
    0.15
     unavoid
    0.15
    Activations Density 0.099%

    No Known Activations