© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 7666
    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
    Negative Logits
    ymi
    -0.28
    究竣
    -0.28
    acos
    -0.27
    æ¼Ķ示
    -0.25
    ourmet
    -0.25
    èĩ³äºİ
    -0.24
    trag
    -0.23
    è¡Į使
    -0.23
    oma
    -0.23
     HOME
    -0.23
    POSITIVE LOGITS
    okus
    0.27
    abella
    0.26
    çļĦ好å¤Ħ
    0.26
    bach
    0.25
    ãĤ¤ãĤ¹
    0.24
    mites
    0.24
    æĹı
    0.24
    rego
    0.24
    buie
    0.23
    好å¤Ħ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.