© 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. 108147
    Prev
    Next
    INDEX
    Explanations

    School levels

    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
    flix
    -0.27
    åŃĹ符
    -0.26
    archy
    -0.26
    åĮħ
    -0.25
    çķĮ
    -0.25
     Thief
    -0.24
    çķĮçļĦ
    -0.24
    (ur
    -0.24
    inions
    -0.24
     packed
    -0.24
    POSITIVE LOGITS
     Wis
    0.28
     hypoth
    0.27
    ãģĻãģ¹
    0.26
    ML
    0.24
     bilateral
    0.23
     either
    0.23
     junior
    0.23
    code
    0.23
     Banc
    0.23
    äºļè¿IJ
    0.23
    Activations Density 3.078%

    No Known Activations