© 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. 52583
    Prev
    Next
    INDEX
    Explanations

    medical and children context

    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
     Interpreter
    -0.30
     interpreter
    -0.28
     rode
    -0.27
    æľŁåĨħ
    -0.27
    .bt
    -0.27
    istor
    -0.26
     curves
    -0.25
    htag
    -0.25
    Tracker
    -0.24
    çļĦä¹IJ趣
    -0.24
    POSITIVE LOGITS
    ,parent
    0.33
    ä¹ī
    0.31
    za
    0.26
    è¦ļ
    0.26
    å»Ĭ
    0.26
    å»ĵ
    0.26
    afa
    0.26
    sandbox
    0.25
    illo
    0.25
    oses
    0.25
    Activations Density 0.004%

    No Known Activations