© 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. 12718
    Prev
    Next
    INDEX
    Explanations

    implantable devices and procedures

    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
    kke
    -0.20
    reten
    -0.20
    å¼ĢçĿĢ
    -0.20
    çĶ¨è½¦
    -0.19
    家åħ·
    -0.19
    etypes
    -0.19
    ngle
    -0.18
    åIJĥäºı
    -0.18
    ricks
    -0.18
    (stdin
    -0.18
    POSITIVE LOGITS
    æ¤įåħ¥
    0.34
    åŁĭ
    0.33
     surg
    0.29
    ç»Ī身
    0.26
    æ°¸ä¹ħ
    0.25
    ç»ĪçĶŁ
    0.22
     titanium
    0.22
    éĴĽ
    0.22
     permanently
    0.22
    åıĸåĩº
    0.22
    Activations Density 0.139%

    No Known Activations