© 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. 54604
    Prev
    Next
    INDEX
    Explanations

    Religion, code, law, politics

    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
    contain
    -0.28
    bsd
    -0.28
    å°ıé¾Ļ
    -0.27
    æĹ¥æĬ¥è®°èĢħ
    -0.27
    èļģ
    -0.26
    Ant
    -0.26
     Ant
    -0.26
    fcc
    -0.26
    楼主
    -0.26
    Contain
    -0.25
    POSITIVE LOGITS
    æĶ¹
    0.32
    istrate
    0.28
    upe
    0.28
    agher
    0.27
    æĻļ
    0.26
    EB
    0.25
    iske
    0.25
     amendment
    0.24
    currentColor
    0.24
    exual
    0.24
    Activations Density 0.007%

    No Known Activations