© 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. 13805
    Prev
    Next
    INDEX
    Explanations

    care following medical or therapy contexts

    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
    åħ¬çĦ¶
    -0.24
    åħīèĬĴ
    -0.22
    åĮħ袱
    -0.22
    ission
    -0.21
    amburger
    -0.21
    令人
    -0.20
    audit
    -0.20
    ropolitan
    -0.20
    使人
    -0.20
    erten
    -0.20
    POSITIVE LOGITS
    é¢Ħéĺ²
    0.28
    çĸĹæ³ķ
    0.27
    æ¯ı天
    0.26
    å°½éĩı
    0.24
    æĹ©æĻļ
    0.24
    åīįåĩłå¤©
    0.24
     помеÑīениÑı
    0.24
    æݪæĸ½
    0.23
    åĩłå¤©
    0.23
    ä¸įè¦ģåĨį
    0.23
    Activations Density 0.041%

    No Known Activations