© 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. 89515
    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
    æŃ£çīĪ
    -0.30
    rike
    -0.29
    ä¸Ģç¬Ķ
    -0.29
     Dual
    -0.27
    ann
    -0.27
    -mode
    -0.26
     manoe
    -0.25
    åŀĭä¼ģä¸ļ
    -0.25
    çľĦ
    -0.24
    åģĪ
    -0.24
    POSITIVE LOGITS
    åľ¨å¤ĸ
    0.26
    clearfix
    0.25
    éĥ¨
    0.25
     Irvine
    0.25
    obi
    0.25
    iasi
    0.25
    quare
    0.25
    tries
    0.24
     Square
    0.24
    byter
    0.24
    Activations Density 7.133%

    No Known Activations

    This feature has no known activations.