© 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. 63425
    Prev
    Next
    INDEX
    Explanations

    Software, 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
    ine
    -0.28
    æĦı大
    -0.26
    alink
    -0.26
    åĪĿè¡·
    -0.25
    orio
    -0.25
    ono
    -0.25
    ynes
    -0.25
    æľī两个
    -0.25
    bach
    -0.24
    .archive
    -0.24
    POSITIVE LOGITS
    æīĵ交éģĵ
    0.28
     toán
    0.27
    =&
    0.27
    åĪĨ辨
    0.26
     expertise
    0.25
    çĬĢ
    0.25
    boxed
    0.24
     zn
    0.24
    heard
    0.24
     kontakt
    0.23
    Activations Density 35.684%

    No Known Activations