© 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. 9054
    Prev
    Next
    INDEX
    Explanations

    Various topics

    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
    á»ĩp
    -0.27
     skÅĤ
    -0.26
     queryInterface
    -0.24
    :;"
    -0.24
    ðŁİĦ
    -0.23
    ONENT
    -0.23
     forgiven
    -0.23
     invokes
    -0.23
    \Active
    -0.22
     dabei
    -0.22
    POSITIVE LOGITS
    asing
    0.27
    ongan
    0.26
    nos
    0.25
     mut
    0.25
    erÃŃa
    0.24
    åħ¥åºĵ
    0.24
    âĢ¦↵
    0.24
     pic
    0.24
    ;<
    0.24
    eria
    0.24
    Activations Density 8.994%

    No Known Activations