© 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. 13859
    Prev
    Next
    INDEX
    Explanations

    code block terminators

    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
    iless
    -0.21
    WISE
    -0.20
     AppConfig
    -0.20
    è¿Ħä»Ĭ
    -0.20
     Encoding
    -0.19
     Brush
    -0.18
    å¾ĺ
    -0.18
    éĻ¢éĻ¢éķ¿
    -0.18
    椿
    -0.18
    acin
    -0.18
    POSITIVE LOGITS
    counter
    0.21
     counter
    0.21
    ä¸į好
    0.20
    FLAG
    0.20
    èĢĴ
    0.20
    æĻ¨
    0.19
    çŃ·
    0.19
    Counter
    0.19
    ä¸ĵ注
    0.19
    .Temp
    0.19
    Activations Density 0.567%

    No Known Activations