© 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. 348
    Prev
    Next
    INDEX
    Explanations

    than

    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
    ForResource
    -0.26
    ersed
    -0.25
     ac
    -0.24
    dle
    -0.23
    .HasKey
    -0.23
    emento
    -0.23
     Jing
    -0.23
    ItemAt
    -0.23
    tent
    -0.23
     Escape
    -0.23
    POSITIVE LOGITS
    xffff
    0.27
    ãģ£ãģ±
    0.27
    POR
    0.26
    ksi
    0.26
    izr
    0.25
    Ont
    0.24
     super
    0.24
    è¿Ľè¡Į
    0.23
     Yard
    0.23
     level
    0.23
    Activations Density 1.065%

    No Known Activations