© 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. 22-TRANSCODER-HP
    7. 112628
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nds
    -0.27
    igans
    -0.27
    çݰ身
    -0.25
    primer
    -0.25
    thern
    -0.24
    åĢ¨
    -0.24
    åĪ¶èį¯
    -0.24
    æĽ´å¤ļ精彩
    -0.24
    appen
    -0.23
    isper
    -0.23
    POSITIVE LOGITS
    äºĭ
    0.28
    Hist
    0.27
     Hist
    0.25
    trap
    0.25
    .contains
    0.24
    æŀľæĸŃ
    0.24
    模åĿĹ
    0.24
    .getBytes
    0.24
    åįķ
    0.24
     byte
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.