© 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. 16620
    Prev
    Next
    INDEX
    Explanations

    medical conditions and disorders

    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
    å¿ħè¦ģ
    -0.21
    å®īå¿ĥ
    -0.19
    æĮĤéĴ©
    -0.19
    éĤ£ä¸ĢåĪ»
    -0.19
     ÑģÑĤоим
    -0.18
    åıĹ欢è¿İ
    -0.18
     ÑĥÑģловиÑı
    -0.18
    ucer
    -0.18
    åĬŀäºĭå¤Ħ
    -0.17
    xfa
    -0.17
    POSITIVE LOGITS
    peed
    0.21
    丢失
    0.21
    ieg
    0.21
    ç²¹
    0.19
     disorder
    0.19
    严éĩįçļĦ
    0.19
    opia
    0.19
    é³Ĭ
    0.19
    _IE
    0.19
    .gs
    0.18
    Activations Density 0.540%

    No Known Activations