© 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. 90271
    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
    heck
    -0.25
     Gall
    -0.25
    stringValue
    -0.25
    æľīéĻIJ责任
    -0.24
    èį¡
    -0.24
    åŃ°
    -0.24
     Cert
    -0.23
     partial
    -0.23
    Cal
    -0.23
     Serial
    -0.23
    POSITIVE LOGITS
    çĬ¹è±«
    0.31
    urat
    0.30
    éľ²
    0.27
    竣工
    0.26
    ULER
    0.26
    æĶ¹åıĺäºĨ
    0.25
    OnInit
    0.25
    ylie
    0.25
     bufsize
    0.24
    æĥĬèī³
    0.24
    Activations Density 1.274%

    No Known Activations

    This feature has no known activations.