© 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. 22-TRANSCODER-HP
    7. 111171
    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
    Negative Logits
    izers
    -0.28
    æĸ¯åŁº
    -0.26
    oble
    -0.26
    istent
    -0.26
    omin
    -0.25
    ach
    -0.25
    æĻ¶
    -0.24
     Su
    -0.24
    unker
    -0.24
     зÑĢ
    -0.24
    POSITIVE LOGITS
    ddit
    0.30
    åıįå°Ħ
    0.25
     vids
    0.25
    æİĢèµ·
    0.25
    collections
    0.25
    è¿Ļè¯Ŀ
    0.25
    èħ±
    0.24
    antis
    0.24
     vej
    0.24
    -caption
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.