© 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. 13553
    Prev
    Next
    INDEX
    Explanations

    aged people elderly

    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
    ãģ¶ãĤĬ
    -0.20
    åĿª
    -0.19
    å·¥ç¨ĭå¸Ī
    -0.18
    å¿ĥè¡Ģ
    -0.17
    éľĩæĴ¼
    -0.17
    åĪĨæīĭ
    -0.17
    ä¸įæ¸ħæ¥ļ
    -0.17
    mr
    -0.17
    山寨
    -0.17
    å±ł
    -0.17
    POSITIVE LOGITS
     aged
    0.22
    ä¸ĵå±ŀ
    0.21
    çĵ®
    0.20
    -age
    0.20
    们
    0.20
    (age
    0.20
    -friendly
    0.20
    çĶ»åĥı
    0.20
    群ä½ĵ
    0.20
    -exclusive
    0.20
    Activations Density 0.017%

    No Known Activations