© 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. 18-TRANSCODER-HP
    7. 88247
    Prev
    Next
    INDEX
    Explanations

    Citation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    веÑģ
    -0.31
    anel
    -0.30
     undert
    -0.30
    _PREVIEW
    -0.28
     Preview
    -0.28
     License
    -0.27
    ...'↵
    -0.27
    ointed
    -0.27
    ...'
    -0.26
    gos
    -0.26
    POSITIVE LOGITS
    åĽ½æľīèµĦ产
    0.28
    icular
    0.26
    对她
    0.25
    è¿Ļå¼ł
    0.25
    åħ¥åѦ
    0.24
    aturday
    0.24
    rama
    0.24
     graph
    0.24
    ang
    0.24
    ics
    0.24
    Activations Density 1.715%

    No Known Activations