© 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. 89843
    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
    Typed
    -0.26
     còn
    -0.25
    çŀİ
    -0.25
     Palmer
    -0.24
    æľīåIJįçļĦ
    -0.24
    裨
    -0.24
    Portal
    -0.24
    _than
    -0.23
    ãģĤãģ£ãģ¦
    -0.23
     mural
    -0.23
    POSITIVE LOGITS
    缺
    0.33
    æĹĹ
    0.27
    isko
    0.25
    åIJ¦å®ļ
    0.25
    aking
    0.25
     His
    0.24
    ling
    0.24
    uen
    0.24
     Leonardo
    0.24
     egt
    0.24
    Activations Density 7.693%

    No Known Activations

    This feature has no known activations.