© 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. 58076
    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
    çļĦå¿ĥæĢģ
    -0.26
     weakSelf
    -0.24
    lest
    -0.23
    bö
    -0.23
     lore
    -0.23
    åħ±èµ¢
    -0.23
    à¹ĥà¸Ī
    -0.23
    ä¹Ĵä¹ĵ
    -0.23
    念
    -0.23
    StreamReader
    -0.22
    POSITIVE LOGITS
    æĿĥåĪ©
    0.75
     rights
    0.73
    çļĦæĿĥåĪ©
    0.66
    rights
    0.63
    æ¬ĬåĪ©
    0.62
     Rights
    0.60
     liberties
    0.60
    Rights
    0.57
    -rights
    0.55
     freedoms
    0.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.