© 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. 89066
    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
    åįĩèµ·
    -0.26
     indu
    -0.26
    [at
    -0.25
    临
    -0.25
    ä¼ļä¸Ĭ
    -0.24
    åģ¿
    -0.24
    èĩ¨
    -0.23
    æĸ°çļĦä¸Ģ
    -0.23
    èī¯å¿ĥ
    -0.23
     Satan
    -0.23
    POSITIVE LOGITS
    alytics
    0.31
    lix
    0.28
    byname
    0.25
    subjects
    0.25
    èĶĵ
    0.24
     vo
    0.24
    .Xml
    0.24
     Lah
    0.24
     subjects
    0.24
    ANTS
    0.24
    Activations Density 0.027%

    No Known Activations

    This feature has no known activations.