© 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. 63763
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    ritt
    -0.26
    éªĩ
    -0.25
    /init
    -0.24
    让她
    -0.24
    æ¿¡
    -0.24
    Tahoma
    -0.24
    egin
    -0.23
    .nc
    -0.23
    iv
    -0.23
    itur
    -0.22
    POSITIVE LOGITS
    Successfully
    0.28
    çIJĨ论
    0.28
    æĶ¿
    0.28
    åĩĨ
    0.27
     Successfully
    0.27
    ppers
    0.26
     Huck
    0.26
    对该
    0.26
    ppo
    0.26
     succesfully
    0.26
    Activations Density 2.963%

    No Known Activations