© 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. 131234
    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
    _place
    -0.26
    /place
    -0.26
     Place
    -0.26
    getRoot
    -0.26
    apia
    -0.25
    pios
    -0.25
     Places
    -0.25
    å¾Ĺ天
    -0.25
    .executor
    -0.25
    Place
    -0.24
    POSITIVE LOGITS
    çIJĨ
    0.31
     wh
    0.28
    orgh
    0.26
    su
    0.26
    ä¸Ģè¡Į
    0.26
    èĭĭ
    0.26
    released
    0.26
    rans
    0.25
    bling
    0.25
    kowski
    0.24
    Activations Density 0.063%

    No Known Activations

    This feature has no known activations.