© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89993
    Prev
    Next
    INDEX
    Explanations

    Formatting/code special characters

    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
    å¨ij
    -0.27
    ght
    -0.27
    æľīèī²
    -0.26
    eme
    -0.25
    etched
    -0.25
    çī¹æĿĥ
    -0.25
    inidad
    -0.25
    å¸ļ
    -0.24
    fter
    -0.24
    åĢ¬
    -0.24
    POSITIVE LOGITS
    èł¡
    0.26
     literals
    0.26
     strings
    0.25
     litt
    0.25
     Ä°s
    0.25
     sustained
    0.24
    çļĦçĶŁæ´»
    0.24
    ypad
    0.23
    轨迹
    0.23
     viewDidLoad
    0.23
    Activations Density 7.697%

    No Known Activations