© 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. 88569
    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°±è·Ł
    -0.28
    ä»ĸå°±
    -0.27
    lse
    -0.26
    就说
    -0.26
    idot
    -0.26
     Gabriel
    -0.25
    å°±è§īå¾Ĺ
    -0.25
     Placeholder
    -0.25
    eroon
    -0.24
    éĻĦåĬłåĢ¼
    -0.24
    POSITIVE LOGITS
     exist
    0.27
    ating
    0.27
    éĻ
    0.27
    åĢ¡è®®
    0.26
    åIJĦæľī
    0.26
    ắng
    0.26
    éĩį
    0.25
    çħ
    0.25
    ))[
    0.25
    è°ģèĥ½
    0.25
    Activations Density 1.950%

    No Known Activations

    This feature has no known activations.