© 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. 14290
    Prev
    Next
    INDEX
    Explanations

    toilet training, waste, bodily functions

    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
    æįĨ
    -0.21
    åħħåĪĨåĪ©çĶ¨
    -0.20
    _fitness
    -0.19
    åħįçĸ«åĬĽ
    -0.19
    é²¥
    -0.18
    loat
    -0.18
    大åĬĽæĶ¯æĮģ
    -0.18
    带åĬ¨
    -0.18
    ç½Ķ
    -0.18
    æ¿ĢçĥĪ
    -0.17
    POSITIVE LOGITS
    好åIJĹ
    0.21
    éļĹ
    0.19
    Rpc
    0.19
    SWG
    0.18
     transition
    0.18
    zion
    0.18
    etz
    0.18
    wick
    0.18
    æ¡©
    0.18
    ebin
    0.17
    Activations Density 0.004%

    No Known Activations