© 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. 16383
    Prev
    Next
    INDEX
    Explanations

    wedding, venue, do, posts, Americans

    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
    .sax
    -0.21
    çĤĴä½ľ
    -0.21
    å°ijåĦ¿
    -0.20
     phẩm
    -0.19
    _SPECIAL
    -0.18
     Authors
    -0.18
    _gp
    -0.18
    .Skin
    -0.18
    çļ®èĤ¤çĹħ
    -0.18
    å´©
    -0.18
    POSITIVE LOGITS
    好åĿı
    0.21
    室å¤ĸ
    0.21
    _estimator
    0.21
    è¿ĽéŨ
    0.20
    åľºåľ°
    0.20
    åĮħ
    0.20
    æĸ¹æ¡Ī
    0.19
    æĹ©æĻ¨
    0.19
    å½ĵ天
    0.19
    é¡¿
    0.19
    Activations Density 0.017%

    No Known Activations