© 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. 12047
    Prev
    Next
    INDEX
    Explanations

    WPA2 Personal, PPP, InnoDB, AES

    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
    é»į
    -0.20
    FromClass
    -0.19
    æ³¢çī¹
    -0.18
     eye
    -0.18
    æ¼ł
    -0.18
    eye
    -0.17
     Eye
    -0.17
    å®ŀæĻ¯
    -0.17
    _ORD
    -0.17
    rag
    -0.17
    POSITIVE LOGITS
    isable
    0.22
    è¿Ļç§į
    0.21
    è¿ĩçļĦ
    0.20
    -equipped
    0.20
    èĩªæķij
    0.19
    åįıè®®
    0.19
    åĮĸçļĦ
    0.18
    æİ©
    0.18
    çĶļèĩ³è¿ŀ
    0.17
    åĮĸ
    0.17
    Activations Density 0.107%

    No Known Activations