© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1844
    Prev
    Next
    INDEX
    Explanations

    types of medical conditions or descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    åľ¨è¿ĩ渡
    -0.26
     uttered
    -0.25
     Broadcasting
    -0.24
    æĮ¥æīĭ
    -0.23
     tweeted
    -0.23
    æĸ°æ¬¾
    -0.23
     begr
    -0.22
     needless
    -0.21
    ellers
    -0.21
    Doing
    -0.21
    POSITIVE LOGITS
    -
    0.25
    ä½ı
    0.25
    alyzed
    0.24
     object
    0.22
    -P
    0.22
     function
    0.22
     P
    0.21
    $(
    0.21
    rive
    0.21
    ä½ľèĢħæīĢæľī
    0.21
    Activations Density 0.752%

    No Known Activations