© 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. 130625
    Prev
    Next
    INDEX
    Explanations

    Technical documentation/code snippets

    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
    约åIJĪ
    -0.25
    thren
    -0.25
    hx
    -0.25
    eous
    -0.25
     różnic
    -0.24
    orca
    -0.24
    uns
    -0.24
    丸
    -0.23
    tls
    -0.23
    sr
    -0.23
    POSITIVE LOGITS
    é
    0.28
    /MIT
    0.27
     tracking
    0.27
     tracks
    0.26
     Tracking
    0.26
    çĦ¶åIJİ
    0.26
    Tracking
    0.25
    è·Łè¸ª
    0.25
     Nation
    0.25
    ến
    0.25
    Activations Density 0.295%

    No Known Activations