© 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. 27-TRANSCODER-HP
    7. 58134
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brisk
    -0.27
    éĩįçİ°
    -0.26
    éĵĬ
    -0.26
     bump
    -0.26
    åĥ»
    -0.25
    .present
    -0.25
     drum
    -0.25
     Buckley
    -0.24
    èĬĤæĹ¥
    -0.24
    .same
    -0.24
    POSITIVE LOGITS
    å±Ģ
    0.28
    è¯Ŀ
    0.28
     Lisbon
    0.27
     Papers
    0.27
    ema
    0.27
     Matches
    0.27
     footer
    0.26
    acement
    0.26
    åĩĮ
    0.26
    æł¼
    0.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.