© 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. 39946
    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
    etu
    -0.27
    olut
    -0.27
    rapy
    -0.26
    èĤĭ
    -0.25
    rap
    -0.24
     Versions
    -0.24
     yaptıģı
    -0.23
    Alignment
    -0.23
    èĥŃ
    -0.23
     Essays
    -0.23
    POSITIVE LOGITS
     fres
    0.28
    æ±ľ
    0.26
    ää
    0.25
    离
    0.25
    že
    0.25
     Fraser
    0.25
    reed
    0.25
    ãģĿãģĨãģł
    0.24
     mv
    0.24
     onDestroy
    0.24
    Activations Density 0.242%

    No Known Activations

    This feature has no known activations.