© 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. 22-TRANSCODER-HP
    7. 129682
    Prev
    Next
    INDEX
    Explanations

    sustainability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iphery
    -0.27
    esan
    -0.25
    resenter
    -0.25
    aign
    -0.25
    æĦıä¹īä¸ĬçļĦ
    -0.25
    éķij
    -0.24
    brero
    -0.24
     Fly
    -0.24
    ä¸įåĨį
    -0.24
    fly
    -0.23
    POSITIVE LOGITS
     Alien
    0.28
    targets
    0.28
     materials
    0.25
    èĤ¤
    0.25
     products
    0.25
    åħī线
    0.24
     subjects
    0.24
    lobals
    0.24
    ,callback
    0.24
    lights
    0.24
    Activations Density 0.002%

    No Known Activations