© 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. 54730
    Prev
    Next
    INDEX
    Explanations

    American

    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
    melon
    -0.27
    åĿĹ
    -0.26
     PROP
    -0.26
    æĦı大
    -0.25
    raph
    -0.24
     drained
    -0.24
    rais
    -0.24
    emma
    -0.24
    åī¯
    -0.24
    -policy
    -0.24
    POSITIVE LOGITS
    ÑĥÑĩ
    0.29
    å·Ŀ
    0.28
    uet
    0.28
    avana
    0.26
    APT
    0.26
    åı®
    0.25
    ars
    0.25
     jihadist
    0.24
    lot
    0.24
     Palace
    0.24
    Activations Density 0.004%

    No Known Activations