© 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. 32-TRANSCODER-HP
    7. 41771
    Prev
    Next
    INDEX
    Explanations

    Brightness/intensity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®
    -0.27
    urement
    -0.27
    广
    -0.25
     wrappers
    -0.25
    ku
    -0.25
    openh
    -0.24
    ERO
    -0.24
     mug
    -0.23
    doing
    -0.23
     Rosenberg
    -0.23
    POSITIVE LOGITS
     raise
    0.28
    æĮ
    0.26
    æł¡
    0.26
    .sup
    0.25
    ç½®äºİ
    0.25
    æĬ¥
    0.24
    puter
    0.24
     bricks
    0.23
     suppose
    0.23
    roups
    0.23
    Activations Density 0.001%

    No Known Activations