© 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. 89208
    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
    SmartPointer
    -0.27
     Cruiser
    -0.25
    -China
    -0.24
    кова
    -0.24
     august
    -0.24
    orbit
    -0.23
     Heller
    -0.23
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.23
    Reached
    -0.23
    HCI
    -0.23
    POSITIVE LOGITS
    ogenesis
    0.28
    less
    0.27
    æĪĺ
    0.25
    odo
    0.25
    rie
    0.24
    ogens
    0.24
    ED
    0.24
    Ø·ÙĦ
    0.24
     muscle
    0.24
    edy
    0.23
    Activations Density 0.021%

    No Known Activations

    This feature has no known activations.