© 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. 89696
    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
    æ¯ķç«Ł
    -0.28
    çļĦæĶ¯æĮģ
    -0.26
    odi
    -0.26
    ovi
    -0.26
    eur
    -0.26
    Ø·ÙĬ
    -0.25
     pil
    -0.25
    å¼ķ导
    -0.24
    åħ¨ç¨ĭ
    -0.24
    irut
    -0.24
    POSITIVE LOGITS
    ework
    0.26
     oath
    0.26
    åĸĿéħĴ
    0.26
    天河
    0.25
    TEE
    0.25
    楹
    0.25
    è¯
    0.24
    ainer
    0.24
    ç¼
    0.23
     mug
    0.23
    Activations Density 4.046%

    No Known Activations

    This feature has no known activations.