© 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. 41113
    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
     dim
    -0.26
     nuclei
    -0.26
    ucz
    -0.25
    unar
    -0.25
    elmet
    -0.25
    éĻ¢åī¯éĻ¢éķ¿
    -0.25
    DetailView
    -0.25
    aidu
    -0.25
    该éĻ¢
    -0.24
     Tracy
    -0.24
    POSITIVE LOGITS
    裳
    0.28
    isk
    0.26
     commission
    0.25
     cancelling
    0.25
     :(
    0.25
     mourning
    0.25
    èIJ
    0.24
    doch
    0.24
    å±ħå§Ķä¼ļ
    0.24
    èĬ¸
    0.24
    Activations Density 4.997%

    No Known Activations

    This feature has no known activations.