© 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. 89390
    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
    å«Įçĸij
    -0.28
     Newest
    -0.27
    horn
    -0.26
     newest
    -0.26
    *time
    -0.26
     drift
    -0.25
    磼
    -0.25
    å°º
    -0.25
    大家ä¸Ģèµ·
    -0.25
    final
    -0.24
    POSITIVE LOGITS
    ä¸ªåĽ½å®¶
    0.31
    å®ľ
    0.26
    ullo
    0.26
     redirects
    0.26
    AREN
    0.25
    hg
    0.25
    glas
    0.24
    æݨèįIJéĺħ读
    0.24
    åľ°ä¸Ńæµ·
    0.24
     written
    0.24
    Activations Density 2.514%

    No Known Activations

    This feature has no known activations.