© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12237
    Prev
    Next
    INDEX
    Explanations

    file paths like /usr/lib and /opt/local

    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
    arning
    -0.21
    产ä¸ļåŁºåľ°
    -0.19
     Cousins
    -0.19
    身
    -0.19
    eer
    -0.19
    èµĶ
    -0.18
     squ
    -0.18
    YouTube
    -0.17
    åĽłåŃIJ
    -0.17
     Colonial
    -0.17
    POSITIVE LOGITS
    доб
    0.26
    adem
    0.18
    кие
    0.18
    -linux
    0.18
    /on
    0.18
     коÑĢ
    0.17
     Ñģимв
    0.17
    驸
    0.17
    ÙĪÙĬÙĦ
    0.17
     ìĦ¤
    0.17
    Activations Density 0.262%

    No Known Activations