© 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. 107321
    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
    rior
    -0.25
    abouts
    -0.25
    .break
    -0.25
    æŃ¤äºº
    -0.25
     draggable
    -0.25
    -SA
    -0.25
    ï¸
    -0.24
    äºĮæ°§åĮĸ
    -0.24
    levant
    -0.24
    lang
    -0.23
    POSITIVE LOGITS
     REFER
    0.31
     tslint
    0.29
    æł¸
    0.29
    ä¸ĢçĤ¹
    0.27
    åŃĺåľ¨çļĦ
    0.27
    newInstance
    0.24
    ç¨į
    0.24
    åİŁèijĹ
    0.24
    ioned
    0.24
    åıĤçħ§
    0.24
    Activations Density 3.354%

    No Known Activations

    This feature has no known activations.