© 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. 8733
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    iaz
    -0.26
     Gros
    -0.25
    èĩªå¦Ĥ
    -0.25
    客æĪ·æıIJä¾Ľ
    -0.24
     Rounds
    -0.24
    åĪ«äººçļĦ
    -0.24
     motivo
    -0.24
    æĭ¾
    -0.24
    chema
    -0.23
    Packages
    -0.23
    POSITIVE LOGITS
    ró
    0.32
    pedia
    0.29
    oron
    0.28
    _hor
    0.26
     åIJ
    0.26
    ComputedStyle
    0.26
     Boom
    0.25
    .Atomic
    0.25
    Hor
    0.24
     '{{
    0.24
    Activations Density 0.222%

    No Known Activations

    This feature has no known activations.