© 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. 130725
    Prev
    Next
    INDEX
    Explanations

    code snippets and file paths

    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
    ä¸ĭ游
    -0.30
     Prospect
    -0.29
    aurus
    -0.28
    @student
    -0.27
    issen
    -0.27
    iously
    -0.26
    athed
    -0.26
     Transcript
    -0.25
    kul
    -0.25
    vim
    -0.25
    POSITIVE LOGITS
    没æľī人
    0.30
    YLE
    0.28
    amd
    0.27
    é¡ĺæĦı
    0.27
    å®ļä½į
    0.26
    没人
    0.25
     organisation
    0.25
    [position
    0.25
     disposition
    0.25
    æľīæĿ¡ä»¶çļĦ
    0.25
    Activations Density 1.430%

    No Known Activations