© 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. 14286
    Prev
    Next
    INDEX
    Explanations

    X-linked disorders

    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
    ç»Ĩ
    -0.20
     provid
    -0.20
    grim
    -0.19
    衲
    -0.19
     Reynolds
    -0.18
    åįģä¸īæĿ¡
    -0.18
    åīĸ
    -0.18
    èIJĺ
    -0.18
    èĤļ
    -0.18
    æİıåĩº
    -0.18
    POSITIVE LOGITS
    女æĢ§
    0.24
    çĶ·æĢ§
    0.23
    าว
    0.23
    æĢ§åĪ«
    0.21
    Balancer
    0.21
     female
    0.20
    female
    0.19
     males
    0.19
    å¦ĩ女
    0.19
     gender
    0.19
    Activations Density 0.026%

    No Known Activations