© 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. 107538
    Prev
    Next
    INDEX
    Explanations

    6

    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
    eman
    -0.28
    ãi
    -0.28
    ardi
    -0.28
     unordered
    -0.26
    igers
    -0.26
    erman
    -0.25
    kt
    -0.25
    åĬ²
    -0.25
    ylan
    -0.24
    tail
    -0.24
    POSITIVE LOGITS
    åĮ¿
    0.30
     Pods
    0.27
    edo
    0.26
    åħ«åįģ
    0.25
    Unless
    0.25
    getMock
    0.25
    她们
    0.24
     subdivisions
    0.23
    èݺ
    0.23
    isoft
    0.23
    Activations Density 74.981%

    No Known Activations