© 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. 56757
    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
    çļĦåľŁåľ°
    -0.29
    æľīä¸Ģ个
    -0.28
    =float
    -0.25
    å®ļçĤ¹
    -0.25
     worlds
    -0.25
    dden
    -0.25
    çļĦ产åĵģ
    -0.25
    .appspot
    -0.24
    ="__
    -0.24
    æĹłç©·
    -0.24
    POSITIVE LOGITS
    emos
    0.25
    æ±Ł
    0.25
     Spacer
    0.24
    ç²¥
    0.24
    lies
    0.23
     modifications
    0.23
    edio
    0.23
    è¿ŁåĪ°
    0.23
    modified
    0.23
    enment
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.