© 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. 11425
    Prev
    Next
    INDEX
    Explanations

    listings of properties or variants

    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
    对åħ¶çľŁå®ŀ
    -0.23
    èĮĥåĨ°
    -0.21
    åĩłæ¬¡
    -0.21
    èİ«
    -0.20
    íĩ´
    -0.20
    pst
    -0.20
    婼
    -0.20
     налогов
    -0.19
    对ä»ĸ们
    -0.19
    ä»»ä½ķ人
    -0.18
    POSITIVE LOGITS
    æķ°åįģ
    0.25
    å®ĿèĹı
    0.25
    æķ°çĻ¾
    0.23
     hundreds
    0.23
    çĻ¾ä½Ļ
    0.22
     tens
    0.22
    ä¸ĬçĻ¾
    0.21
    ä¸ĩåįĥ
    0.21
     dozens
    0.20
    åĪĨå¸ĥåľ¨
    0.20
    Activations Density 0.301%

    No Known Activations