© 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. 41122
    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
    èݽ
    -0.27
     Dur
    -0.26
    ogh
    -0.26
    flow
    -0.26
     Formal
    -0.25
    éĤ»éĩĮ
    -0.25
     stir
    -0.24
    mue
    -0.24
    çľĭä¸įåĩº
    -0.24
     sucks
    -0.24
    POSITIVE LOGITS
    [at
    0.26
    $rs
    0.26
    iper
    0.26
    idine
    0.24
    ãĥIJãĥ¼
    0.24
    Merit
    0.24
    raries
    0.24
    ä»ĭè´¨
    0.23
    (exit
    0.23
    _gettime
    0.23
    Activations Density 2.195%

    No Known Activations

    This feature has no known activations.