© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9654
    Prev
    Next
    INDEX
    Explanations

    Names, companies, and schools

    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
    Negative Logits
    ATTER
    -0.26
    åķĦ
    -0.26
    REN
    -0.24
    åĪĻæĺ¯
    -0.24
    roids
    -0.24
    WithPath
    -0.24
    zos
    -0.24
    astes
    -0.24
    éĻĦ
    -0.24
    ASTE
    -0.23
    POSITIVE LOGITS
    ...'
    0.28
    侧éĿ¢
    0.25
    èĢĮåĩº
    0.25
    _CONSTANT
    0.25
     Sanford
    0.25
     loạn
    0.25
    #endregion
    0.24
    iration
    0.24
    罩
    0.24
     apl
    0.24
    Activations Density 0.032%

    No Known Activations