© 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. 16563
    Prev
    Next
    INDEX
    Explanations

    gas, smell, and biological processes

    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
    æŃ£åĵģ
    -0.21
    æłijèĦĤ
    -0.19
    ê¶Į
    -0.18
    奥æŀĹ
    -0.18
    æ´¼
    -0.18
    å¹´æĬ¥
    -0.18
    ç¼Ķ
    -0.18
    黯
    -0.18
     resil
    -0.18
    éºĴéºŁ
    -0.18
    POSITIVE LOGITS
     gases
    0.24
     gas
    0.24
     fart
    0.21
     od
    0.20
     Semantic
    0.20
    æ°Ķä½ĵ
    0.19
     emitted
    0.19
     semantic
    0.19
    çĹķ
    0.19
     odor
    0.19
    Activations Density 0.009%

    No Known Activations