© 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. 18-TRANSCODER-HP
    7. 88927
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teenth
    -0.33
    ilogy
    -0.31
    anche
    -0.28
    rale
    -0.28
    iline
    -0.28
    anning
    -0.26
    ailer
    -0.24
    atern
    -0.24
    Quit
    -0.24
    alog
    -0.24
    POSITIVE LOGITS
     favourite
    0.28
     neighbours
    0.27
    对ä»ĸ
    0.26
    å¾Ĺèµ·
    0.25
     revealing
    0.25
    pps
    0.25
     neighbour
    0.24
    éĤ»å±ħ
    0.24
     school
    0.24
     himself
    0.24
    Activations Density 5.190%

    No Known Activations

    This feature has no known activations.