© 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. 89251
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    orie
    -0.28
     adversaries
    -0.25
    rome
    -0.25
    .IntPtr
    -0.25
    xDB
    -0.24
    sets
    -0.24
    å·¥ä½ľä»»åĬ¡
    -0.24
    ordinates
    -0.24
     DIE
    -0.24
    owa
    -0.23
    POSITIVE LOGITS
    {(
    0.28
     detailed
    0.25
    æľ¬èº«å°±æĺ¯
    0.24
    eson
    0.24
     ↵    ↵
    0.24
    Declared
    0.24
     {(
    0.24
    _strlen
    0.23
    符åIJĪ
    0.23
    poss
    0.23
    Activations Density 20.147%

    No Known Activations

    This feature has no known activations.