© 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. 39939
    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
    elson
    -0.28
    æĿ¡ä»¶ä¸ĭ
    -0.27
    -bo
    -0.26
    çļĦè¯Ŀ
    -0.26
    欢è¿İæĤ¨
    -0.25
     elder
    -0.25
    der
    -0.24
     ques
    -0.24
    临
    -0.24
    åı°åĮĹ
    -0.23
    POSITIVE LOGITS
    arkan
    0.28
     hawk
    0.26
    çĽij管éĥ¨éŨ
    0.26
     Covers
    0.26
     astronomers
    0.25
    uft
    0.25
    ×Ļ׳×Ķ
    0.25
    лен
    0.25
    argin
    0.24
    containers
    0.24
    Activations Density 0.049%

    No Known Activations

    This feature has no known activations.