© 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. 54815
    Prev
    Next
    INDEX
    Explanations

    code/configuration files

    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
     proven
    -0.29
     tang
    -0.28
     cod
    -0.28
     bran
    -0.28
     tape
    -0.28
    tic
    -0.27
    ICI
    -0.27
     dialog
    -0.27
     indexed
    -0.27
    atica
    -0.27
    POSITIVE LOGITS
    ah
    0.30
    åij½è¿IJ
    0.29
    ariat
    0.28
    ahas
    0.27
    apolis
    0.26
     speculation
    0.26
    -na
    0.25
     drains
    0.24
    èľķ
    0.24
     parties
    0.24
    Activations Density 0.008%

    No Known Activations