© 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. 90323
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
    neau
    -0.27
    èĤĭ
    -0.26
    amed
    -0.24
    usta
    -0.24
    éd
    -0.24
    ç¥ĸ
    -0.24
    åħµåĽ¢
    -0.24
     slate
    -0.24
    beck
    -0.24
    ä»»åĬ¡
    -0.24
    POSITIVE LOGITS
    á»Ĵ
    0.31
    å¿«ä¸ī
    0.29
    indsight
    0.27
    tram
    0.26
    midt
    0.25
    ä¸Ģåħ±
    0.25
    BOTTOM
    0.24
    ÑĭÑĪ
    0.24
    PAD
    0.24
    ormap
    0.23
    Activations Density 0.104%

    No Known Activations

    This feature has no known activations.