© 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. 129759
    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
     Ballard
    -0.27
    ETCH
    -0.27
    ernet
    -0.26
    niÄĻ
    -0.26
    essions
    -0.26
    engo
    -0.26
    èĪŁ
    -0.25
    èĢĮ对äºİ
    -0.25
    ILES
    -0.25
    ès
    -0.25
    POSITIVE LOGITS
    çļĦçĶŁæ´»
    0.28
    ingleton
    0.28
    çĶŁæ´»
    0.26
    æŀķ
    0.26
     Detective
    0.25
    ë¸Į
    0.25
    avity
    0.25
    æĹłçĸij
    0.24
    inner
    0.24
    elp
    0.24
    Activations Density 39.429%

    No Known Activations

    This feature has no known activations.