© 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. 18-TRANSCODER-HP
    7. 89071
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owering
    -0.27
    缧
    -0.26
    Äħc
    -0.25
    ’hui
    -0.25
    flen
    -0.24
     Laboratories
    -0.24
    AZE
    -0.24
     Trib
    -0.24
    ä¼ģä¸ļæıIJä¾Ľ
    -0.23
    åį¢
    -0.23
    POSITIVE LOGITS
    ilik
    0.29
     beat
    0.27
    ä¸ŃéĹ´
    0.25
     Wrest
    0.25
     namely
    0.24
    its
    0.24
    :block
    0.23
    _MSK
    0.23
    åĪĨåĪ«æĺ¯
    0.23
    us
    0.23
    Activations Density 0.077%

    No Known Activations

    This feature has no known activations.