© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88743
    Prev
    Next
    INDEX
    Explanations

    code/programming fragments

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĬĽè¿ĺæĺ¯
    -0.25
    _ALWAYS
    -0.25
    IsRequired
    -0.23
     alloys
    -0.23
    _reserved
    -0.23
    BackPressed
    -0.23
    .breakpoints
    -0.22
    à¸ģำ
    -0.22
    å¤©åºľ
    -0.22
     Insider
    -0.22
    POSITIVE LOGITS
    ि
    0.25
    dat
    0.24
    nio
    0.24
    idan
    0.24
    åIJĿ
    0.23
    Mac
    0.23
    numbers
    0.23
    l
    0.23
    ef
    0.23
    rl
    0.22
    Activations Density 76.132%

    No Known Activations