© 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. 53738
    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
     Transform
    -0.29
    Transformation
    -0.29
     Transformation
    -0.28
    å½»åºķ
    -0.28
    YPE
    -0.27
    ivet
    -0.26
    å¯Įæ°ij
    -0.26
     transformation
    -0.25
    转åıĺ
    -0.25
     transformative
    -0.25
    POSITIVE LOGITS
    NC
    0.30
    åĵī
    0.29
    azers
    0.28
     NC
    0.27
     dece
    0.26
    èĩªæľī
    0.26
    èĢĥ
    0.26
    /place
    0.26
    /end
    0.26
    zelf
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.