© 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. 33-TRANSCODER-HP
    7. 54584
    Prev
    Next
    INDEX
    Explanations

    medical situations/patients

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     living
    -0.43
     lived
    -0.37
     lives
    -0.36
    living
    -0.35
    Living
    -0.32
    æ´»
    -0.32
    -live
    -0.31
     live
    -0.31
     Living
    -0.30
    èĭŀ
    -0.30
    POSITIVE LOGITS
    åīįçŀ»æĢ§
    0.33
    zew
    0.30
    tested
    0.29
    onica
    0.27
    -testing
    0.26
    nge
    0.26
    onso
    0.25
    uktur
    0.25
    ä¸ļ
    0.25
     Had
    0.25
    Activations Density 0.017%

    No Known Activations