© 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. 40898
    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
     tán
    -0.27
    pher
    -0.27
    lobber
    -0.26
     subjected
    -0.26
     fidelity
    -0.25
    oto
    -0.24
     Succ
    -0.24
    -flash
    -0.24
    atab
    -0.24
    hee
    -0.23
    POSITIVE LOGITS
    '",
    0.26
     paran
    0.26
     securely
    0.25
    ste
    0.25
    æĦıæĢĿ
    0.24
     built
    0.24
     mill
    0.24
     conn
    0.24
     ste
    0.23
    dü
    0.23
    Activations Density 1.101%

    No Known Activations

    This feature has no known activations.