© 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. 31-TRANSCODER-HP
    7. 19135
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lek
    -0.27
    为ä»Ģä¹Īä¸į
    -0.27
    atomy
    -0.27
    顾
    -0.26
    LES
    -0.26
    amics
    -0.25
    -pointer
    -0.25
    iton
    -0.25
     itself
    -0.25
    Æ¡i
    -0.25
    POSITIVE LOGITS
     thereafter
    0.30
     deductible
    0.27
    cakes
    0.27
    -rate
    0.26
     afterwards
    0.26
     recogn
    0.25
     Accident
    0.25
     sustaining
    0.25
     afterward
    0.25
    ride
    0.25
    Activations Density 0.896%

    No Known Activations

    This feature has no known activations.