© 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. 19-TRANSCODER-HP
    7. 8955
    Prev
    Next
    INDEX
    Explanations

    source code/documentation with numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stag
    -0.27
    ÑģÑĤÑĮ
    -0.26
    .createFrom
    -0.25
    reamble
    -0.25
     Predict
    -0.24
     Associ
    -0.24
    omat
    -0.24
     Serie
    -0.23
    ØŃÙĥ
    -0.23
     Detected
    -0.23
    POSITIVE LOGITS
    å®ģåİ¿
    0.29
    sit
    0.27
    è§Ĩ
    0.27
    atz
    0.27
    itionally
    0.25
    iov
    0.24
    çļĦåĬ¨åĬĽ
    0.24
    иÑĤÑģÑı
    0.24
    cy
    0.24
    ViewSet
    0.23
    Activations Density 0.003%

    No Known Activations