© 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. 14771
    Prev
    Next
    INDEX
    Explanations

    gratitude and closings

    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
    ÑĦи
    -0.19
    odate
    -0.19
    Rare
    -0.19
    REFERENCES
    -0.18
    uate
    -0.18
     Welfare
    -0.18
     ime
    -0.18
    åĨ³
    -0.18
    å½¢
    -0.18
    åĪĨ为
    -0.18
    POSITIVE LOGITS
    OND
    0.21
    éħ±æ²¹
    0.20
    glas
    0.20
    楼ä¸Ĭ
    0.19
    å²ģ以ä¸Ĭ
    0.19
    OSC
    0.18
    èĩªçĦ¶æĺ¯
    0.18
     katılı
    0.18
    çļ´
    0.18
    çĥŃå¿ĥ
    0.17
    Activations Density 0.017%

    No Known Activations