© 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. 13338
    Prev
    Next
    INDEX
    Explanations

    announcements and releases

    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
    æĪijè¿ĺæĺ¯
    -0.23
    诰
    -0.20
    ä»Ģä¹ĪæĦıæĢĿ
    -0.20
    åħ¬åĬ¡åijĺ
    -0.20
    eways
    -0.19
    ä»ħ次äºİ
    -0.19
    .onError
    -0.19
    æĪij们è¦ģ
    -0.19
    isbn
    -0.19
    å¸Ī
    -0.19
    POSITIVE LOGITS
    çİ°å¦Ĥä»Ĭ
    0.20
    æŀģåħ·
    0.20
    _GENERIC
    0.20
    å´Ń
    0.20
    åıijçİ°
    0.20
    çĪĨ
    0.20
    ätt
    0.20
    _PROVID
    0.19
    åħ¨æĸ°çļĦ
    0.19
    åıijçİ°äºĨ
    0.19
    Activations Density 0.046%

    No Known Activations