© 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. 7748
    Prev
    Next
    INDEX
    Explanations

    Locations and levels

    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
    abo
    -0.24
     wink
    -0.24
    èĦIJ
    -0.24
    à¹Ģร
    -0.24
     Sox
    -0.24
     tug
    -0.24
    айл
    -0.23
    yx
    -0.23
     Grade
    -0.23
    verage
    -0.23
    POSITIVE LOGITS
    izione
    0.31
    bih
    0.28
    imity
    0.27
    hol
    0.27
     kidding
    0.25
    é¢ł
    0.25
    stras
    0.25
     charms
    0.25
    åij
    0.25
    .Navigator
    0.24
    Activations Density 0.131%

    No Known Activations