© 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. 88666
    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
     NOTICE
    -0.29
    hti
    -0.28
    oble
    -0.27
     tom
    -0.26
    èħ¾
    -0.26
    éĨī
    -0.25
    uarios
    -0.25
    >()->
    -0.25
     redis
    -0.25
    lane
    -0.24
    POSITIVE LOGITS
    è¿ĻäºĽä¸ľè¥¿
    0.29
     @{↵
    0.27
    è¿Ļåĩł
    0.26
     meilleur
    0.26
    ogue
    0.25
    SWG
    0.25
    kj
    0.25
    _DETECT
    0.23
    为æĬĵ
    0.23
    åĸĿæ°´
    0.23
    Activations Density 10.413%

    No Known Activations

    This feature has no known activations.