© 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. 16192
    Prev
    Next
    INDEX
    Explanations

    overlapping elements

    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
    ifications
    -0.20
    itative
    -0.20
    ÑģÑĭ
    -0.19
    æĥķ
    -0.16
    liness
    -0.16
    éĦľ
    -0.16
    å§Ķä¼ļ
    -0.15
    izations
    -0.15
    ä¸Ģåī¯
    -0.15
    åIJİåı°
    -0.15
    POSITIVE LOGITS
    ingly
    0.32
    ï¸
    0.17
    edException
    0.17
    æīĭæİĮ
    0.17
    åľ°å¸¦
    0.17
    ecs
    0.16
    æĭ³å¤´
    0.16
    çģ«åĬĽ
    0.16
    rosse
    0.16
    å¯Įè£ķ
    0.16
    Activations Density 0.043%

    No Known Activations