© 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. 88458
    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
    Not in Any Lists

    No Comments

    Negative Logits
    涸
    -0.28
     cra
    -0.27
    ospace
    -0.26
    举
    -0.26
     favour
    -0.25
    icrosoft
    -0.25
    éĿĴçĿIJ
    -0.24
     Oval
    -0.24
     citas
    -0.24
    è¯Į
    -0.23
    POSITIVE LOGITS
    饴
    0.27
    emann
    0.27
    ç½
    0.26
    ç³»
    0.25
    ockets
    0.25
    çļĦéĤ£ä¸ª
    0.24
    ¹Ħ
    0.24
    รà¸ģ
    0.23
    paging
    0.23
    å±
    0.23
    Activations Density 7.568%

    No Known Activations

    This feature has no known activations.