© 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. 30-TRANSCODER-HP
    7. 95934
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ń
    -0.27
    éªĬ
    -0.27
     ther
    -0.27
    aravel
    -0.26
    un
    -0.26
     primarily
    -0.25
    enal
    -0.25
    榴
    -0.24
    æĽ¿
    -0.23
    olib
    -0.23
    POSITIVE LOGITS
    SEQUENTIAL
    0.34
    å§Ĭ妹
    0.25
    -</
    0.25
    enta
    0.24
    protocol
    0.24
     tren
    0.24
     protocol
    0.23
    ses
    0.23
    sequ
    0.23
    cko
    0.23
    Activations Density 0.881%

    No Known Activations

    This feature has no known activations.