© 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. 22-TRANSCODER-HP
    7. 111125
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Ử
    -0.28
    åı¦
    -0.26
     frustrations
    -0.25
     makeup
    -0.25
    raq
    -0.24
    licer
    -0.24
     sorts
    -0.23
    åı¦å¤ĸ
    -0.23
     coordinate
    -0.23
    -IS
    -0.23
    POSITIVE LOGITS
    çĹĩ
    0.36
    éĢ¢
    0.29
    hyp
    0.27
    rosis
    0.25
    terior
    0.25
    度
    0.25
    apter
    0.25
    触åıĬ
    0.25
    .sec
    0.25
    Persistence
    0.25
    Activations Density 0.126%

    No Known Activations