© 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. 90136
    Prev
    Next
    INDEX
    Explanations

    Contact information

    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
    éĤ£ç§į
    -0.26
     cents
    -0.26
    lvl
    -0.26
    utas
    -0.26
    _device
    -0.25
    Device
    -0.24
    outed
    -0.24
    æĵ¢
    -0.23
    DC
    -0.23
    æĥ³èµ·æĿ¥
    -0.23
    POSITIVE LOGITS
    ugins
    0.31
    çĽ²
    0.28
     oe
    0.24
    对æĪij们
    0.24
    weise
    0.24
    书åĨĻ
    0.24
    -times
    0.24
    Sea
    0.24
    çħ
    0.24
    quist
    0.24
    Activations Density 2.005%

    No Known Activations