© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 336
    Prev
    Next
    INDEX
    Explanations

    Barn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ressing
    -0.29
    æĬķæľº
    -0.27
    usty
    -0.25
    ress
    -0.25
    Validation
    -0.24
    opro
    -0.23
    emark
    -0.23
    atorial
    -0.23
    .Obj
    -0.23
    entrant
    -0.23
    POSITIVE LOGITS
    eneg
    0.27
    istes
    0.26
    ugg
    0.26
     fet
    0.25
    iste
    0.25
    serter
    0.24
    stants
    0.24
    lices
    0.24
     corridors
    0.24
    aths
    0.23
    Activations Density 0.013%

    No Known Activations