© 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. 13265
    Prev
    Next
    INDEX
    Explanations

    outside or beyond

    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
    oyer
    -0.21
    acha
    -0.19
    รา
    -0.19
    æŶåĪ»
    -0.19
     impro
    -0.19
    æĹłè®º
    -0.18
    ожно
    -0.18
    缸å½ĵäºİ
    -0.18
    æľīäºĽ
    -0.18
    åıĮéĩį
    -0.18
    POSITIVE LOGITS
    å±ĢéĻIJäºİ
    0.23
     than
    0.22
    äºİæѤ
    0.22
    ä¹ĭå¤ĸ
    0.22
    halb
    0.21
    -than
    0.20
    æĪijä¸į
    0.20
    ä¼łç»Ł
    0.20
    than
    0.20
    æĪijä¸įæĥ³
    0.20
    Activations Density 0.141%

    No Known Activations