© 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. 110991
    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
    ération
    -0.26
    Today
    -0.26
     deg
    -0.26
     realised
    -0.25
    ä¸įéĢļ
    -0.25
    emos
    -0.24
    æĭ¼
    -0.24
     chữ
    -0.24
    opies
    -0.24
    aning
    -0.24
    POSITIVE LOGITS
    ä¸Ĭ线
    0.28
    lander
    0.27
    -Ta
    0.27
    /arm
    0.27
    æĹĹä¸ĭ
    0.26
     Pull
    0.26
    arrant
    0.26
    åħļåĨħ
    0.26
    /rs
    0.26
    ulin
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.