© 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. 88101
    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
    oning
    -0.28
    iture
    -0.28
     ge
    -0.28
    çļĦæĥħæĦŁ
    -0.27
    -generic
    -0.26
    åIJ¦å®ļ
    -0.26
    /copyleft
    -0.25
    typ
    -0.25
    attributes
    -0.25
     typo
    -0.25
    POSITIVE LOGITS
    agus
    0.26
    as
    0.26
     ÐĴедÑĮ
    0.25
    essler
    0.24
    preter
    0.24
    ãĥ¼ãĤ¸
    0.24
    .Bus
    0.24
     fathers
    0.24
    icious
    0.24
    ä¹Łä¼ļ
    0.23
    Activations Density 7.362%

    No Known Activations

    This feature has no known activations.