© 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. 57911
    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
    alle
    -0.29
     DeV
    -0.29
    avia
    -0.28
     partial
    -0.27
    immel
    -0.26
     paper
    -0.26
    身
    -0.25
    纸
    -0.25
     kuk
    -0.24
    indy
    -0.23
    POSITIVE LOGITS
     ante
    0.38
     arc
    0.37
     leo
    0.33
     odio
    0.31
     nisi
    0.30
     eros
    0.30
    estroy
    0.30
     aug
    0.29
     massa
    0.29
    Nib
    0.29
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.