© 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. 89188
    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
    ä¸į满
    -0.29
     Cra
    -0.28
    gy
    -0.26
     Scrolls
    -0.26
     IDD
    -0.25
    æĢĴ
    -0.25
     nextPage
    -0.25
    fal
    -0.24
    çĪ·
    -0.24
    -visible
    -0.24
    POSITIVE LOGITS
    unist
    0.29
    åħ¬çĽĬæ´»åĬ¨
    0.28
     sino
    0.27
    wh
    0.26
     passing
    0.25
    ä½ķ
    0.24
    ost
    0.24
    èĩ³ä»Ĭ
    0.23
    å¥ł
    0.23
    kest
    0.23
    Activations Density 0.042%

    No Known Activations

    This feature has no known activations.