© 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. 15953
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Opens
    -0.22
    InView
    -0.21
    opa
    -0.20
    顶å±Ĥ设计
    -0.20
     hunts
    -0.19
    褫
    -0.18
     digs
    -0.18
    egra
    -0.18
    emy
    -0.18
    liqu
    -0.17
    POSITIVE LOGITS
    èĹķ
    0.20
    è´¶
    0.20
    æĺ¶
    0.20
     exagger
    0.20
    æ¼ı
    0.19
    åĪģ
    0.19
    çĮĸ
    0.19
    mdl
    0.18
     suite
    0.18
    .unknown
    0.18
    Activations Density 0.000%

    No Known Activations