© 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. 88233
    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
    å¢ĥ
    -0.29
    ä¸ĢèĤ¡
    -0.27
    PageRoute
    -0.26
    agos
    -0.26
    fts
    -0.26
    fen
    -0.25
    ä¸ĢåĪĨ
    -0.25
    LEV
    -0.24
     tents
    -0.24
    uxe
    -0.24
    POSITIVE LOGITS
     awakened
    0.27
    iper
    0.27
    omon
    0.24
     organizer
    0.24
    IFA
    0.24
    碰æĴŀ
    0.24
    neg
    0.24
    ä»ij
    0.24
    çĴŀ
    0.24
     Organizer
    0.24
    Activations Density 4.019%

    No Known Activations

    This feature has no known activations.