© 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. 40446
    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
     throughout
    -0.27
    wat
    -0.27
    amo
    -0.26
     downstream
    -0.26
    mouth
    -0.25
    ί
    -0.25
    limit
    -0.25
    tsky
    -0.25
    issa
    -0.25
    amen
    -0.24
    POSITIVE LOGITS
    éĤ£ä¹Ī容æĺĵ
    0.30
    该éĻ¢
    0.28
    设æĸ½å»ºè®¾
    0.27
    贪婪
    0.26
    ç¿ĺ
    0.26
    à¹Ģย
    0.26
    EFR
    0.25
    è¿Ļå¼ł
    0.25
    orage
    0.25
    为ä¼ģä¸ļ
    0.25
    Activations Density 0.249%

    No Known Activations

    This feature has no known activations.