© 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. 13751
    Prev
    Next
    INDEX
    Explanations

    African American institutions and history

    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
    æĬĬä»ĸ
    -0.23
    æĬĬä½ł
    -0.23
    FromArray
    -0.21
    è´¥
    -0.20
     conflict
    -0.20
    éĺ²çĽĹ
    -0.20
     Trib
    -0.19
    rend
    -0.19
    æ±ķ
    -0.18
    coli
    -0.18
    POSITIVE LOGITS
     bakım
    0.23
    è´¨åľ°
    0.22
    çĨŁ
    0.22
    iales
    0.21
    ä¸Ģå¹´ä¸Ģ度
    0.20
    é¢Ľ
    0.19
    èijŃ
    0.19
    andas
    0.19
    ä¸ĵå±ŀ
    0.18
    åĹ¡
    0.18
    Activations Density 0.018%

    No Known Activations