© 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. 130029
    Prev
    Next
    INDEX
    Explanations

    Technical/Specialized domains

    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
    zo
    -0.26
    åĮĿ
    -0.26
    .beh
    -0.25
    amp
    -0.25
    Arial
    -0.24
     profitable
    -0.24
    ihil
    -0.23
    æĶ¹
    -0.23
     gamm
    -0.23
    çĽĸ
    -0.23
    POSITIVE LOGITS
    ç¿ķ
    0.27
    Ìģ
    0.26
    _ED
    0.26
    åĮĻ
    0.25
    CLI
    0.25
     Fundamental
    0.25
    CUS
    0.25
    éĻī
    0.23
     Essential
    0.23
     Endpoint
    0.23
    Activations Density 19.684%

    No Known Activations