© 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. 54836
    Prev
    Next
    INDEX
    Explanations

    views

    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
     views
    -0.36
    View
    -0.36
     View
    -0.35
     Views
    -0.34
    Views
    -0.33
    views
    -0.33
    _views
    -0.32
     VIEW
    -0.32
     view
    -0.32
    .View
    -0.31
    POSITIVE LOGITS
    [frame
    0.34
     offshore
    0.29
     frames
    0.29
     Accessed
    0.28
    cmds
    0.28
    å±ħ
    0.28
    itable
    0.27
    帧
    0.27
    ablish
    0.26
    assing
    0.26
    Activations Density 0.024%

    No Known Activations