© 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. 129778
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    港åĮº
    -0.30
    pite
    -0.29
    æīĵçĿĢ
    -0.26
    NDER
    -0.25
    arde
    -0.25
    pared
    -0.25
    缸éĢļ
    -0.25
    clin
    -0.25
    åĴ©
    -0.24
    æī«é»ij
    -0.24
    POSITIVE LOGITS
     iss
    0.26
    ìĬµ
    0.26
    ocab
    0.26
     Grammy
    0.25
    oling
    0.24
     Dew
    0.23
    æŁ¥çľĭæĽ´å¤ļ
    0.23
    вÑıз
    0.23
     Diss
    0.23
     chief
    0.23
    Activations Density 52.565%

    No Known Activations

    This feature has no known activations.