© 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. 89096
    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
    nist
    -0.32
    eel
    -0.28
    ä¸ªé¡¹çĽ®
    -0.26
    æĬķèµĦé¡¹çĽ®
    -0.26
    åīįéĶĭ
    -0.26
    ее
    -0.24
    ä¹ĭåľ°
    -0.24
    \Events
    -0.23
     evid
    -0.23
     translator
    -0.23
    POSITIVE LOGITS
    iterate
    0.26
    **č↵
    0.24
    rians
    0.24
     **/↵
    0.24
    æŬ
    0.24
    ç«Ļéķ¿
    0.24
     cotton
    0.23
    fox
    0.23
     butterfly
    0.23
    ionic
    0.23
    Activations Density 11.274%

    No Known Activations

    This feature has no known activations.