© 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. 14518
    Prev
    Next
    INDEX
    Explanations

    doping Agency

    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
    eral
    -0.22
     unfinished
    -0.20
    å´©
    -0.19
     chol
    -0.19
    isco
    -0.19
    ç»ĥ
    -0.19
    åĩłä¸ªäºº
    -0.18
     Chop
    -0.18
    åIJµ
    -0.18
    UPI
    -0.18
    POSITIVE LOGITS
     detected
    0.21
    å¢ĥå¤ĸ
    0.21
    èĪµ
    0.21
    eree
    0.21
    éħİ
    0.20
    æĵħ
    0.20
    æ£Ģæµĭ
    0.20
    ä»İä¸ļ
    0.19
    eda
    0.19
    éļIJå½¢
    0.19
    Activations Density 0.011%

    No Known Activations