© 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. 16236
    Prev
    Next
    INDEX
    Explanations

    sign, signed, signature

    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
    æ¦Ķ
    -0.22
    åĽŀ头
    -0.21
    kim
    -0.21
    讨
    -0.19
    ziej
    -0.19
    榫
    -0.18
     Glenn
    -0.18
    à¤Ľ
    -0.18
    vang
    -0.18
    .apple
    -0.17
    POSITIVE LOGITS
    èµĬ
    0.21
    æĺī
    0.20
    大æĸ¹
    0.19
    ов
    0.19
    åıĹ害
    0.19
    ä¸ĢéĹ´
    0.19
     labyrinth
    0.18
    è°ĥåĬ¨
    0.18
    ä½İè°ĥ
    0.18
    çݰ代çī©æµģ
    0.18
    Activations Density 0.002%

    No Known Activations