© 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. 88279
    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
    Negative Logits
     traditionally
    -0.28
     perpetual
    -0.26
    -pill
    -0.26
    åħħåĪĨä½ĵçİ°
    -0.26
    为ä¸Ģä½ĵ
    -0.25
    ä¸ĢåIJij
    -0.25
    ä¸ĢæĬĬ
    -0.25
    为主线
    -0.23
    èĭŀ
    -0.23
     degrees
    -0.23
    POSITIVE LOGITS
    ...',↵
    0.30
     ?',
    0.28
    _',
    0.27
    uger
    0.27
    !',↵
    0.27
     <",
    0.26
    åIJĪä½ľ
    0.26
    ç®Ĺæ³ķ
    0.25
    ysz
    0.25
    ...',
    0.25
    Activations Density 11.247%

    No Known Activations

    This feature has no known activations.