© 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. 88706
    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
     ties
    -0.28
     masses
    -0.28
    åį¿
    -0.27
    èĢĥãģĪãĤĭ
    -0.26
    æŶä¸į
    -0.25
    _EOF
    -0.25
    ilogy
    -0.24
     min
    -0.24
    æ³ģ
    -0.24
     Tie
    -0.24
    POSITIVE LOGITS
    åĢŁ
    0.26
    ;y
    0.25
    íĦ´
    0.24
     SVN
    0.24
    ,strong
    0.24
     viet
    0.23
     Carter
    0.23
    å·©
    0.23
    äºĨä¸Ģæī¹
    0.23
    =value
    0.23
    Activations Density 26.192%

    No Known Activations

    This feature has no known activations.