© 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. 90185
    Prev
    Next
    INDEX
    Explanations

    Acronyms

    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
    udo
    -0.28
    _te
    -0.26
    icolor
    -0.25
    hy
    -0.25
    çĶ°
    -0.24
    身边
    -0.24
    èĹı
    -0.24
    踦
    -0.23
    -centered
    -0.23
     Towers
    -0.23
    POSITIVE LOGITS
    onis
    0.35
    ney
    0.27
    eler
    0.27
    olon
    0.26
    LEX
    0.26
    rive
    0.25
    unas
    0.25
    lias
    0.25
    OMB
    0.25
    opi
    0.25
    Activations Density 11.590%

    No Known Activations