© 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. 57477
    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
    cribes
    -0.29
     Perr
    -0.27
    ëĭ´
    -0.26
    ÅĽni
    -0.26
    terr
    -0.26
     underneath
    -0.25
    under
    -0.24
    yntax
    -0.24
     CPF
    -0.24
    ideos
    -0.24
    POSITIVE LOGITS
    é¼ĵèĪŀ
    0.27
    ÑĤиÑĢов
    0.27
     getItem
    0.25
    ç«ĭ
    0.25
     Dar
    0.24
    姥
    0.24
    ä¼łæĴŃ
    0.23
     Atmos
    0.23
    ëĮĢë¡ľ
    0.23
    sandbox
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.