© 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. 12371
    Prev
    Next
    INDEX
    Explanations

    players' solutions process VER of our

    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
    åħ·æľīèī¯å¥½
    -0.22
    æī¶
    -0.21
    ä¹ĸ
    -0.19
     TPP
    -0.19
    _parts
    -0.19
    é¥Ń
    -0.18
    è°ħ
    -0.18
    oko
    -0.18
     дело
    -0.18
    æĪĸå¤ļ
    -0.18
    POSITIVE LOGITS
    .asp
    0.21
     Kỳ
    0.20
    ä¸ĸ纪
    0.20
    èĥĦ
    0.20
    çħŀ
    0.18
    ç»ıå¼Ģ
    0.18
     Parallel
    0.18
    æIJºæīĭ
    0.18
    ︰
    0.18
    ordon
    0.17
    Activations Density 0.536%

    No Known Activations