© 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. 56334
    Prev
    Next
    INDEX
    Explanations

    code and configuration files

    np_max-act-logits · gemini-2.0-flash
    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
    uen
    -0.26
     bou
    -0.26
    enth
    -0.26
    endor
    -0.26
    åį°è±¡
    -0.25
     /↵
    -0.25
     Huffington
    -0.24
    NavController
    -0.24
    nar
    -0.24
     Flam
    -0.23
    POSITIVE LOGITS
    ä¿Ŀ温
    0.34
    éĩĩ
    0.28
     gim
    0.27
     æŁ¥
    0.25
     üzere
    0.25
    ixin
    0.24
    Ãłnh
    0.24
    _HOME
    0.24
     tai
    0.24
    gratis
    0.24
    Activations Density 0.104%

    No Known Activations