© 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. 63701
    Prev
    Next
    INDEX
    Explanations

    appears

    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
     siblings
    -0.27
     cir
    -0.27
    noc
    -0.26
    èħĮ
    -0.26
    çĪ±äºº
    -0.25
    emplo
    -0.24
     yourselves
    -0.24
    reas
    -0.24
     ePub
    -0.23
    	View
    -0.23
    POSITIVE LOGITS
    åIJĮæŶ
    0.26
    opl
    0.26
    ha
    0.26
    -dr
    0.25
    getColumn
    0.25
    ToOne
    0.24
    getKey
    0.24
    CodeAt
    0.24
    roid
    0.24
    对ä»ĸ们
    0.24
    Activations Density 60.134%

    No Known Activations