© 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. 54702
    Prev
    Next
    INDEX
    Explanations

    the

    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
     chế
    -0.30
    asti
    -0.27
    æĶ¿
    -0.26
    åĮħ
    -0.25
    isci
    -0.25
    rep
    -0.25
    æļij
    -0.24
    bal
    -0.24
    oley
    -0.24
    ç«Ń
    -0.24
    POSITIVE LOGITS
     final
    0.47
    final
    0.38
    	final
    0.34
     Final
    0.33
    _final
    0.32
    æľĢç»Ī
    0.30
    -final
    0.29
    Final
    0.29
    .final
    0.29
    éĴİ
    0.28
    Activations Density 0.011%

    No Known Activations