© 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. 52615
    Prev
    Next
    INDEX
    Explanations

    immunology and cells

    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
    Plate
    -0.31
    ambi
    -0.28
    Hat
    -0.28
    壳
    -0.28
     Terrace
    -0.28
    NgModule
    -0.27
    hat
    -0.27
     Swift
    -0.27
     plate
    -0.27
     Plate
    -0.26
    POSITIVE LOGITS
    nets
    0.34
    net
    0.31
     net
    0.30
    ç«Ļéķ¿
    0.29
    åħ·ä½ĵåĨħ容
    0.29
     ph
    0.29
    å°ıåºĹ
    0.29
    ç½ij
    0.28
    俨
    0.27
    網
    0.27
    Activations Density 0.053%

    No Known Activations