© 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. 52586
    Prev
    Next
    INDEX
    Explanations

    make

    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
    åĮ¡
    -0.23
    enos
    -0.23
    帮æĪij
    -0.22
    æĤ¨åIJĮæĦı
    -0.22
    æĦıè§ģåıįé¦Ī
    -0.22
    å²ĺ
    -0.21
    _war
    -0.21
    Portrait
    -0.20
    blocks
    -0.20
    season
    -0.20
    POSITIVE LOGITS
     make
    1.49
     makes
    1.42
     making
    1.42
    make
    1.40
    Make
    1.35
    	make
    1.34
     Make
    1.34
    .make
    1.27
    making
    1.26
     Making
    1.24
    Activations Density 0.174%

    No Known Activations