© 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. 130409
    Prev
    Next
    INDEX
    Explanations

    Beginning of sentences

    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
     activations
    -0.25
    éļIJ约
    -0.25
    åıł
    -0.25
    mps
    -0.24
    æIJħ
    -0.24
    _DI
    -0.23
    YPES
    -0.23
     há»Ļ
    -0.23
     horrors
    -0.23
    为人
    -0.23
    POSITIVE LOGITS
    arcy
    0.30
    tabs
    0.30
    æĽĿ
    0.28
    kids
    0.27
    .PO
    0.25
    ramid
    0.24
    Touches
    0.24
    <>(
    0.24
    SetBranch
    0.24
     único
    0.24
    Activations Density 0.265%

    No Known Activations