© 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. 25-TRANSCODER-HP
    7. 108278
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hart
    -0.29
    hardt
    -0.27
    æĪIJ交
    -0.27
    esz
    -0.26
    arity
    -0.26
    bler
    -0.25
    licate
    -0.25
    onacci
    -0.25
    æĸ°åįİ
    -0.25
    /Branch
    -0.25
    POSITIVE LOGITS
    港åĮº
    0.29
    ãĤ¹ãĥĨ
    0.24
    åħ¨çľģ
    0.24
    åıĮçľ¼
    0.24
    cala
    0.23
     Klo
    0.23
     Essentially
    0.23
    Mine
    0.23
     MouseEventArgs
    0.23
    æĴŀ
    0.23
    Activations Density 0.317%

    No Known Activations

    This feature has no known activations.