© 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. 142176
    Prev
    Next
    INDEX
    Explanations

    years

    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
    /><
    -0.28
    ico
    -0.25
    h
    -0.25
    scar
    -0.25
    yped
    -0.25
    BarController
    -0.24
     hardly
    -0.23
    .Ptr
    -0.23
     lot
    -0.23
     wake
    -0.23
    POSITIVE LOGITS
    eselect
    0.32
    宣讲
    0.29
    è¬Ľ
    0.29
    .null
    0.28
    è£Ĩ
    0.28
    éĢīæĭ
    0.27
    -outs
    0.26
     appropriate
    0.26
    appropriate
    0.25
    oles
    0.25
    Activations Density 1.706%

    No Known Activations