© 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. 15141
    Prev
    Next
    INDEX
    Explanations

    retreat getaway

    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
    ãģĦãĤĭ
    -0.23
    ãģıãĤĮ
    -0.19
    teenth
    -0.19
    çĺŁ
    -0.18
    太快
    -0.18
    åģĥ
    -0.18
    彤
    -0.17
     تعاÙĦÙī
    -0.17
    ến
    -0.17
    nect
    -0.17
    POSITIVE LOGITS
    ESH
    0.20
    INESS
    0.19
    rzy
    0.18
    ODB
    0.17
    ividad
    0.17
    ÑģоÑģ
    0.17
    omatic
    0.17
    ocz
    0.16
    utra
    0.16
    ublic
    0.16
    Activations Density 0.001%

    No Known Activations