© 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. 15309
    Prev
    Next
    INDEX
    Explanations

    legal responsibility and consequences

    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
    åıĸå¾Ĺ以åıĬ
    -0.23
    èµİ
    -0.21
    åħijçİ°
    -0.21
    éĸĭæĶ¾
    -0.20
    INTERFACE
    -0.20
    åĢĻ
    -0.20
     اÙĦآخر
    -0.20
    ZY
    -0.19
    åħ¨çIJĥç»ıæµİ
    -0.19
    èµ°
    -0.19
    POSITIVE LOGITS
    è¦ģçľĭ
    0.21
    è¡¡
    0.20
    åݦ
    0.20
    lashes
    0.19
    éĢĤçĶ¨
    0.19
     reckon
    0.19
    樾
    0.19
    èļ±
    0.19
    æĽ¦
    0.19
     Jeh
    0.18
    Activations Density 0.049%

    No Known Activations