© 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. 52530
    Prev
    Next
    INDEX
    Explanations

    address

    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
    éĹ®é¢ĺ
    -0.38
    åķıé¡Į
    -0.36
    .problem
    -0.32
    Problem
    -0.32
     problem
    -0.31
    problem
    -0.31
     Issue
    -0.30
    éĹ®é¢ĺæĺ¯
    -0.30
     issue
    -0.30
    (problem
    -0.30
    POSITIVE LOGITS
     head
    0.34
     the
    0.34
     this
    0.33
     these
    0.31
     ideas
    0.30
     key
    0.28
     features
    0.28
     many
    0.28
     core
    0.28
     queries
    0.28
    Activations Density 0.031%

    No Known Activations