© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40650
    Prev
    Next
    INDEX
    Explanations

    medical ailments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    客æłĪ
    -0.31
    åĴĮæľįåĬ¡
    -0.29
    ((_
    -0.27
     the
    -0.27
    åĮ¿åIJį
    -0.26
    ,},↵
    -0.26
    ä¸įå®Į
    -0.26
    设
    -0.25
    设置äºĨ
    -0.25
    èµŀåĬ©
    -0.25
    POSITIVE LOGITS
     infections
    0.42
     seizures
    0.39
     arthritis
    0.39
     fractures
    0.39
     hypertension
    0.38
     diseases
    0.37
     tumors
    0.37
     cancers
    0.37
     infection
    0.36
     disorders
    0.35
    Activations Density 3.552%

    No Known Activations