© 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. 11171
    Prev
    Next
    INDEX
    Explanations

    phone and device names

    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
    è¤Ĵ
    -0.21
    éģij
    -0.20
     ust
    -0.20
    åĮ¾
    -0.20
    .operations
    -0.20
    olas
    -0.19
     machinery
    -0.19
    èijĨ
    -0.19
     rust
    -0.18
    kiye
    -0.18
    POSITIVE LOGITS
    表çİ°
    0.22
    schlü
    0.21
    ensex
    0.20
    麸
    0.20
    第äºĮ次
    0.20
    عدÙĦ
    0.20
    оÑī
    0.20
    æĹłç¼ĺ
    0.20
    å¼ķè¿Ľ
    0.20
    çļĦ表çİ°
    0.19
    Activations Density 0.028%

    No Known Activations