© 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. 14-TRANSCODER-HP
    7. 40188
    Prev
    Next
    INDEX
    Explanations

    The letter "j"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éķĸ
    -0.29
    è°·
    -0.27
    ales
    -0.26
    次
    -0.25
    \Exceptions
    -0.25
    createQueryBuilder
    -0.25
    .instances
    -0.25
     caus
    -0.25
    ucha
    -0.24
     gx
    -0.24
    POSITIVE LOGITS
    вÑĪиÑģÑĮ
    0.28
     discretion
    0.27
     walmart
    0.25
    æĪĺ
    0.25
    åįıè°ĥ
    0.24
    isible
    0.24
    oes
    0.24
    father
    0.24
    agger
    0.24
     Alvarez
    0.24
    Activations Density 0.037%

    No Known Activations