© 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. 33-TRANSCODER-HP
    7. 52647
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è§Ĵ度
    -0.28
    MAS
    -0.27
    Kick
    -0.25
    为äºĨ让
    -0.25
    ={`/
    -0.25
    UnderTest
    -0.24
    иков
    -0.24
    å¤§åľ°
    -0.24
    quil
    -0.24
    åĽ´
    -0.24
    POSITIVE LOGITS
    她说
    0.28
    -offs
    0.26
    ires
    0.26
    nÃŃ
    0.26
    åłª
    0.26
    -off
    0.25
    chalk
    0.25
     off
    0.25
    åĨµ
    0.25
    ç«ł
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.