© 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. 53175
    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
    OOM
    -0.28
    wc
    -0.27
    *f
    -0.26
    -Tr
    -0.26
    rame
    -0.25
    éģ½
    -0.25
    (Frame
    -0.24
     Pierce
    -0.24
    cales
    -0.24
     AUTHORS
    -0.24
    POSITIVE LOGITS
    积
    0.28
    åĿ³
    0.26
    ,tp
    0.26
    ä¸įå¼Ģ
    0.25
     Belgi
    0.24
    éľīç´ł
    0.24
    ä¾
    0.24
    èī¯
    0.24
    æĮĩåIJij
    0.24
    å¼Ģ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.