© 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. 89194
    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
    èĬŃ
    -0.27
     comments
    -0.27
     intentions
    -0.25
     ÃŃch
    -0.25
    пÑĢоÑģ
    -0.25
    ç¦
    -0.25
    æł·
    -0.24
    ãĥŃãĥ¼
    -0.24
    åģľçķĻ
    -0.24
    æĶ¹æŃ£
    -0.24
    POSITIVE LOGITS
    бÑĥÑĢ
    0.28
    å¡ŀ
    0.27
    osterone
    0.27
    ucker
    0.26
    æ´¾
    0.26
    aldi
    0.24
    adero
    0.24
    emm
    0.23
    ongan
    0.23
    æĪĺ士
    0.23
    Activations Density 11.418%

    No Known Activations

    This feature has no known activations.