© 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. 52768
    Prev
    Next
    INDEX
    Explanations

    Right

    np_max-act-logits · gemini-2.0-flash
    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
     right
    -0.69
    right
    -0.63
     Right
    -0.62
    Right
    -0.59
    åı³
    -0.52
    	right
    -0.52
    _right
    -0.51
     RIGHT
    -0.50
    _Right
    -0.48
    RIGHT
    -0.47
    POSITIVE LOGITS
     next
    0.29
    ä¸ĭä¸Ģ
    0.28
    -of
    0.27
     form
    0.26
    âĢ¦)
    0.26
    çķĻç»Ļ
    0.25
     {}:
    0.25
    åIJĥçļĦ
    0.25
    sh
    0.24
    [next
    0.24
    Activations Density 0.017%

    No Known Activations