© 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. 16361
    Prev
    Next
    INDEX
    Explanations

    friends and family

    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
    rzy
    -0.22
    妥åĸĦ
    -0.19
    [++
    -0.19
    oire
    -0.19
     ARTICLE
    -0.18
    é¢Ħå¤ĩ
    -0.18
    åħijçİ°
    -0.18
    å¾ĢåIJİ
    -0.18
    /sc
    -0.18
    technical
    -0.18
    POSITIVE LOGITS
    好åıĭ
    0.24
    åİĨå¹´
    0.21
    list
    0.19
    رÙĨ
    0.19
    çľĭä¸Ģçľĭ
    0.19
    lap
    0.19
    æĶĢçĻ»
    0.19
    like
    0.18
    tri
    0.18
    compatible
    0.18
    Activations Density 0.001%

    No Known Activations