© 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. 13919
    Prev
    Next
    INDEX
    Explanations

    court rulings

    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
    grown
    -0.22
    èµ·æĿ¥äºĨ
    -0.19
    earch
    -0.18
    hood
    -0.17
    utton
    -0.17
    _highlight
    -0.17
    pulse
    -0.17
    åħ¨å¥Ĺ
    -0.17
    pires
    -0.16
    lots
    -0.16
    POSITIVE LOGITS
     rằng
    0.24
    лем
    0.20
    éĻŁ
    0.20
    ä¸Ģ声
    0.19
    nable
    0.19
    IDD
    0.17
    ndef
    0.16
    неÑģен
    0.16
    人身
    0.16
    avel
    0.16
    Activations Density 0.031%

    No Known Activations