© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54087
    Prev
    Next
    INDEX
    Explanations

    technical writing snippets

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å±ħ
    -0.27
    aff
    -0.27
     Inspired
    -0.26
    .framework
    -0.25
    æ·¡åĮĸ
    -0.24
     letto
    -0.23
     stil
    -0.23
    SDK
    -0.23
    amide
    -0.23
    æĪĸå¤ļæĪĸå°ij
    -0.23
    POSITIVE LOGITS
    pons
    0.28
    emin
    0.25
    setSize
    0.25
    pora
    0.25
     phys
    0.24
    å¤ļå¹´çļĦ
    0.24
    ến
    0.24
    主æĮģ人
    0.24
    uales
    0.24
    Em
    0.24
    Activations Density 0.020%

    No Known Activations