© 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. 15021
    Prev
    Next
    INDEX
    Explanations

    loss or theft

    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
     glfw
    -0.19
    оÑĢа
    -0.19
    åī
    -0.19
    inery
    -0.19
    VES
    -0.18
     Compression
    -0.18
    _migration
    -0.18
    ajes
    -0.18
    è¿ĩåī©
    -0.18
    éĽį
    -0.17
    POSITIVE LOGITS
    丢失
    0.41
    æįŁå¤±
    0.31
     loss
    0.29
    丢äºĨ
    0.28
     lost
    0.27
     Loss
    0.27
    Lost
    0.26
     Lose
    0.26
    æįŁèĢĹ
    0.26
     losses
    0.25
    Activations Density 0.024%

    No Known Activations