© 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. 9304
    Prev
    Next
    INDEX
    Explanations

    audience

    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
     foundations
    -0.26
    ÙĪغ
    -0.25
    le
    -0.24
     Fault
    -0.23
    codes
    -0.22
    äºĨå¾Īå¤ļ
    -0.22
     Foundations
    -0.22
     Expression
    -0.22
     Relationships
    -0.22
     salv
    -0.22
    POSITIVE LOGITS
    orate
    0.25
    æł¼å±Ģ
    0.23
     drives
    0.23
    å¤Ļ
    0.23
    META
    0.23
    -serving
    0.23
    /lists
    0.22
    qml
    0.22
    alom
    0.22
    /off
    0.22
    Activations Density 2.717%

    No Known Activations