© 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. 130049
    Prev
    Next
    INDEX
    Explanations

    varied, unrelated text excerpts

    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
     owl
    -0.28
    CONS
    -0.26
     coming
    -0.26
    彤
    -0.25
     Coming
    -0.24
     overtime
    -0.24
    ipes
    -0.24
    аÑĪ
    -0.23
    åıªè§ģ
    -0.23
     Ton
    -0.23
    POSITIVE LOGITS
     Freeman
    0.25
    auty
    0.24
     vale
    0.24
    åIJī祥
    0.24
    nc
    0.24
    felt
    0.23
     besides
    0.23
    oit
    0.23
    ãģ¡
    0.23
    棣
    0.23
    Activations Density 48.133%

    No Known Activations