© 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. 129489
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    cepts
    -0.28
    iless
    -0.26
    abant
    -0.26
    erate
    -0.26
    rier
    -0.25
     datatable
    -0.25
     Principle
    -0.25
    æĺĻ
    -0.25
     dispatched
    -0.24
    ä¸ĢåĪ»
    -0.24
    POSITIVE LOGITS
    çªĿ
    0.27
    cli
    0.26
    permit
    0.26
     Hodg
    0.24
     Kelvin
    0.23
    å¤ļãģĦ
    0.22
    usted
    0.22
    acje
    0.22
     ![
    0.22
    ittel
    0.22
    Activations Density 0.951%

    No Known Activations