© 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. 20-TRANSCODER-HP
    7. 63657
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    outes
    -0.29
    åIJĪä¸Ģ
    -0.28
     brick
    -0.28
     immediate
    -0.27
    ç£Ĭ
    -0.26
     minute
    -0.26
    ounters
    -0.25
    ctal
    -0.25
    arda
    -0.25
    cka
    -0.25
    POSITIVE LOGITS
    -TV
    0.27
    EFR
    0.26
    çĶµè§Ĩ
    0.26
     tv
    0.26
    æĬ¥åijĬæĺ¾ç¤º
    0.26
     HeaderComponent
    0.25
    ROS
    0.25
    gal
    0.25
    æĸĩçĮ®
    0.24
     CFG
    0.24
    Activations Density 57.115%

    No Known Activations