© 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. 57025
    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
     runes
    -0.25
    stile
    -0.25
     replicas
    -0.24
    çķľ
    -0.24
    oload
    -0.24
    ¢åįķ
    -0.24
    PUR
    -0.23
     Spells
    -0.23
    istles
    -0.23
    oler
    -0.23
    POSITIVE LOGITS
    dem
    0.26
    amed
    0.25
     Tuấn
    0.24
    峡
    0.24
     çe
    0.23
     FCC
    0.23
    æĺİæĹ¥
    0.23
    ÉĶ
    0.23
    posix
    0.23
     <!
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.