© 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. 89064
    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
    *)_
    -0.28
    åģļåĩº
    -0.26
    天ä¸ĭ
    -0.24
    ATALOG
    -0.24
    atalog
    -0.24
    è¨Ģ
    -0.24
    åºķä¸ĭ
    -0.24
    URN
    -0.23
    ¦Ĥ
    -0.23
    antic
    -0.23
    POSITIVE LOGITS
     receiver
    0.28
    åĵ¼
    0.26
     accident
    0.26
     initials
    0.25
     RECEIVER
    0.25
    åıĸå¾ĹäºĨ
    0.25
    ç½
    0.24
    顺
    0.24
    chant
    0.24
    kv
    0.24
    Activations Density 3.753%

    No Known Activations

    This feature has no known activations.