© 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. 35-TRANSCODER-HP
    7. 40527
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¼Ĥè®®
    -0.24
    强大
    -0.23
    çķĻä½ı
    -0.23
     stain
    -0.23
    大家
    -0.23
    æĥħ
    -0.22
     sticky
    -0.22
     vant
    -0.22
    .share
    -0.22
    oth
    -0.22
    POSITIVE LOGITS
    ä½ľèĢħæīĢæľī
    0.27
     []),↵
    0.24
    ...",↵
    0.24
    ...">↵
    0.23
    ipur
    0.22
     Trafford
    0.22
     {.
    0.21
    RICS
    0.21
    åIJı
    0.21
     Warsaw
    0.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.