© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88600
    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
    hel
    -0.29
     UUID
    -0.28
    elm
    -0.26
     accompanies
    -0.26
    UUID
    -0.25
    æĸĩåĮĸèīºæľ¯
    -0.24
    lington
    -0.24
    arta
    -0.24
    phabet
    -0.24
    æĢ»çĽij
    -0.24
    POSITIVE LOGITS
    æľĪä¸Ń
    0.29
    omat
    0.28
    ctp
    0.26
    imen
    0.25
    ominator
    0.25
    ÃĨ
    0.24
    Ø·ÙĤ
    0.24
    .lat
    0.24
    $t
    0.23
    仲
    0.23
    Activations Density 2.231%

    No Known Activations

    This feature has no known activations.