© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88288
    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
    Negative Logits
    modifier
    -0.27
    -ing
    -0.26
    acks
    -0.25
    ainen
    -0.24
    æĥħ人
    -0.24
    åĨ¢
    -0.24
     ÑĢаздел
    -0.24
     ([]
    -0.24
    嵬
    -0.24
    Router
    -0.24
    POSITIVE LOGITS
    ä¹ĭæīĢ以
    0.27
    åīįçŀ»æĢ§
    0.26
    elta
    0.25
     lil
    0.25
    _fa
    0.25
     Getter
    0.24
    æģģ
    0.24
    å·¥èµĦ
    0.24
    说å¾Ĺ
    0.23
    thur
    0.23
    Activations Density 1.363%

    No Known Activations

    This feature has no known activations.