© 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. 52648
    Prev
    Next
    INDEX
    Explanations

    materials science

    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
    onis
    -0.27
    gren
    -0.27
    磮
    -0.26
    涯
    -0.26
    éĽĨåĽ¢èĤ¡ä»½
    -0.26
    å°ijåĦ¿
    -0.25
    ocrat
    -0.25
     Capitals
    -0.25
    legacy
    -0.25
    鼨
    -0.24
    POSITIVE LOGITS
     ret
    0.29
     Hex
    0.28
    ret
    0.27
     pall
    0.27
    dig
    0.27
     hex
    0.27
     sod
    0.26
    Hex
    0.25
    CP
    0.25
    PO
    0.25
    Activations Density 0.084%

    No Known Activations