© 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. 89023
    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
    Priv
    -0.31
    quat
    -0.30
    æ·±åĪ»
    -0.29
    Stick
    -0.26
     privé
    -0.26
    uby
    -0.25
    .Ribbon
    -0.24
     Rica
    -0.24
    åħ«ä¸ª
    -0.24
    UBLIC
    -0.24
    POSITIVE LOGITS
    太å¤ļäºĨ
    0.27
    该éĻ¢
    0.26
    è¶Ĭå¤ļ
    0.26
    esis
    0.26
    èģŀ
    0.26
    è½½
    0.25
    諸
    0.25
    çļĦ缮åħī
    0.25
    éĹ»
    0.25
    ä¹ĭ乡
    0.25
    Activations Density 5.503%

    No Known Activations

    This feature has no known activations.