© 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. 88511
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    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
    developers
    -0.27
     Near
    -0.26
    еÑģÑĤв
    -0.26
     near
    -0.25
     Abe
    -0.25
    .presentation
    -0.24
    æµĭ
    -0.24
    åīįæıIJæĺ¯
    -0.24
    SessionFactory
    -0.24
    尽头
    -0.24
    POSITIVE LOGITS
    åIJijå¤ĸ
    0.40
     backward
    0.35
     backwards
    0.33
     reverse
    0.32
    åIJijä¸ĭ
    0.29
     обÑĢаÑĤ
    0.29
    reverse
    0.29
     forwards
    0.28
    å¾ĢæĿ¥
    0.28
    ä¸ĭ乡
    0.27
    Activations Density 50.178%

    No Known Activations