© 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. 14253
    Prev
    Next
    INDEX
    Explanations

    death penalty and row

    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
    诡
    -0.19
    stä
    -0.18
    æłijæľ¨
    -0.18
    æĸ°çļĦ
    -0.17
    éĥ½æľīèĩªå·±
    -0.17
    CCR
    -0.17
    getattr
    -0.17
    çľĭæľĽ
    -0.17
    /spec
    -0.17
    å¨ĺ家
    -0.17
    POSITIVE LOGITS
    æİĪ
    0.22
    缴èĩ³
    0.19
    ugal
    0.18
    avit
    0.18
     verdict
    0.18
    RICT
    0.18
    éĢĤçĶ¨äºİ
    0.18
    çĶļ
    0.18
    clusive
    0.18
    æ°ijäºĭ
    0.18
    Activations Density 0.004%

    No Known Activations