© 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. 23-TRANSCODER-HP
    7. 25103
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conversion
    -0.26
     Variation
    -0.24
    ctrine
    -0.24
    dio
    -0.23
     Alignment
    -0.23
     Flags
    -0.23
     kir
    -0.23
    pirit
    -0.23
     Supply
    -0.23
    Sin
    -0.23
    POSITIVE LOGITS
     opaque
    0.26
     jet
    0.26
    abella
    0.25
    åİ¿åħ¬å®īå±Ģ
    0.25
    igers
    0.24
     rates
    0.24
    ucha
    0.23
     alo
    0.23
    let
    0.23
     masses
    0.23
    Activations Density 1.041%

    No Known Activations

    This feature has no known activations.