© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54089
    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
    Not in Any Lists

    No Comments

    Negative Logits
    -than
    -0.29
     Spokane
    -0.26
     paran
    -0.26
    colo
    -0.26
    ROUGH
    -0.24
    _mk
    -0.24
    око
    -0.23
    ç¼£
    -0.23
    _CNTL
    -0.23
    isable
    -0.23
    POSITIVE LOGITS
    é¢Ħå¤ĩ
    0.30
     Preparation
    0.28
    mlink
    0.25
     distribution
    0.25
    ç¼ĸ
    0.25
     Subject
    0.25
     занима
    0.24
    ynchronized
    0.24
    chains
    0.24
    liced
    0.24
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.