© 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. 2837
    Prev
    Next
    INDEX
    Explanations

    possible treatment or use of medicine

    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
    çľĭæĿ¥
    -0.23
    ä¾ĿéĿł
    -0.23
    Due
    -0.22
    çľĭä¸Ĭåİ»
    -0.21
    [frame
    -0.21
    èĢĢçľ¼
    -0.21
     stabilize
    -0.20
     оÑĤмеÑĤ
    -0.20
    Regardless
    -0.20
    æŀķ
    -0.20
    POSITIVE LOGITS
     topics
    0.43
    æѤäºĭ
    0.38
     topic
    0.36
    topics
    0.36
    äºĭå®ľ
    0.33
     matters
    0.32
    -topic
    0.31
    topic
    0.31
    çļĦè¯Ŀé¢ĺ
    0.31
    缸åħ³åĨħ容
    0.29
    Activations Density 0.269%

    No Known Activations