© 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. 14-TRANSCODER-HP
    7. 41144
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ander
    -0.28
    å°»
    -0.28
    .rl
    -0.28
    onium
    -0.28
    .ul
    -0.27
    ä¸įåıĺ
    -0.26
    æľĢæĸ°çļĦ
    -0.26
    彤
    -0.26
    wise
    -0.25
    车éĺŁ
    -0.24
    POSITIVE LOGITS
    seealso
    0.28
    å°±æĿ¥çľĭçľĭ
    0.28
    itational
    0.27
    溺
    0.27
    gings
    0.26
    MAS
    0.25
     Yourself
    0.25
    -provider
    0.24
     Portug
    0.24
    ä¸Ģåı¥
    0.23
    Activations Density 0.036%

    No Known Activations

    This feature has no known activations.