© 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. 12008
    Prev
    Next
    INDEX
    Explanations

    historical contexts and dates

    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
     Geile
    -0.23
    æĭĽ
    -0.23
    让ä»ĸ们
    -0.22
    æ´ĽæĿī
    -0.21
     expected
    -0.20
    åĸģ
    -0.20
    #af
    -0.19
    geist
    -0.19
     expect
    -0.19
     à¹Ģมษ
    -0.19
    POSITIVE LOGITS
    åİĨåı²
    0.32
    history
    0.30
    æŃ·åı²
    0.28
    æ¸Ĭ
    0.27
    histor
    0.27
     history
    0.26
    çļĦåİĨåı²
    0.26
    åı²æĸĻ
    0.26
    è®°è½½
    0.25
    æľĢæĹ©çļĦ
    0.25
    Activations Density 0.049%

    No Known Activations