© 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. 13891
    Prev
    Next
    INDEX
    Explanations

    enron

    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
    _EXPI
    -0.20
    eting
    -0.19
    æİıåĩº
    -0.19
    åij·
    -0.19
    arsing
    -0.18
     richest
    -0.18
    aben
    -0.18
    çĮ·
    -0.18
    æ·Ļ
    -0.18
    鸳
    -0.18
    POSITIVE LOGITS
    人çĶŁçļĦ
    0.19
    äºĨèĩªå·±çļĦ
    0.19
    éĵ¶è¡Į
    0.19
    欣æħ°
    0.18
    æ¡£
    0.18
    çIJĨ念
    0.18
    dep
    0.18
    åľºåľ°
    0.18
    åĽ¾ä¹¦é¦Ĩ
    0.17
    éĻ¤æѤä¹ĭå¤ĸ
    0.17
    Activations Density 0.005%

    No Known Activations