© 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. 57797
    Prev
    Next
    INDEX
    Explanations

    frame/framework

    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
    Not in Any Lists

    No Comments

    Negative Logits
     speculate
    -0.27
    LLL
    -0.25
    æĥ§
    -0.25
    emean
    -0.24
    enger
    -0.24
    ugh
    -0.24
    thanks
    -0.24
    itä
    -0.23
    fans
    -0.23
    /GL
    -0.22
    POSITIVE LOGITS
    æīĢæıIJä¾ĽçļĦ
    0.25
    æıIJä¾ĽçļĦ
    0.25
    å¦ĤæѤ
    0.25
    æľīåĬ©
    0.25
    æīĢæıIJä¾Ľ
    0.24
     лиÑĨ
    0.24
    egot
    0.23
    ä¾
    0.23
    åįģ足
    0.23
    ponsor
    0.23
    Activations Density 1.276%

    No Known Activations