© 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. 89519
    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
    äºĨä»ĸçļĦ
    -0.28
    retweeted
    -0.27
    amework
    -0.26
    astics
    -0.26
    aways
    -0.26
    ses
    -0.25
    ðŁĺĺ
    -0.24
     discre
    -0.24
    ãģĦãģŁãģłãģįãģ¾ãģĹãģŁ
    -0.24
    áf
    -0.24
    POSITIVE LOGITS
    illet
    0.27
    à¸ļาà¸Ĺ
    0.26
     ISO
    0.26
    arat
    0.26
    banana
    0.26
    rat
    0.26
    ISO
    0.25
     arbit
    0.25
    QM
    0.25
     insan
    0.24
    Activations Density 57.330%

    No Known Activations

    This feature has no known activations.