© 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. 89159
    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
    ogo
    -0.29
    eu
    -0.28
    eted
    -0.27
    鼷æĸ¯
    -0.26
     vest
    -0.26
    PUTE
    -0.25
    quia
    -0.25
    ä¸ĭåİ»
    -0.25
    stead
    -0.25
    été
    -0.24
    POSITIVE LOGITS
    æİĴ
    0.30
     tops
    0.27
    èģĶéĢļ
    0.26
    è°
    0.26
    moment
    0.24
     nowhere
    0.24
    åı£å²¸
    0.24
    ä¸įåľ¨ä¹İ
    0.24
    prep
    0.23
    æĹłæīĢè°ĵ
    0.23
    Activations Density 34.361%

    No Known Activations

    This feature has no known activations.