© 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. 52792
    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
    讣
    -0.25
    ILED
    -0.25
     Called
    -0.25
    nett
    -0.24
     Rabbi
    -0.23
     bitterness
    -0.23
    ANN
    -0.23
    nette
    -0.23
     ká»ĥ
    -0.23
    pname
    -0.23
    POSITIVE LOGITS
    conde
    0.30
    feit
    0.28
     pref
    0.27
    å¼ķ
    0.27
    æ±ĩéĽĨ
    0.26
    BarItem
    0.26
     prere
    0.26
    mith
    0.26
    BarController
    0.26
    uum
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.