© 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. 130155
    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
    RK
    -0.26
    åºķ
    -0.25
    æѧ
    -0.24
    (%
    -0.24
    sville
    -0.24
     tl
    -0.24
    uck
    -0.24
    esus
    -0.24
    ares
    -0.23
    %(
    -0.23
    POSITIVE LOGITS
    inton
    0.26
    ç»ĥ
    0.25
    âĸ¾
    0.24
     manageable
    0.23
     app
    0.22
     provinces
    0.22
    ãģ©ãģ®
    0.22
     unp
    0.22
    ög
    0.22
     contiguous
    0.22
    Activations Density 20.191%

    No Known Activations

    This feature has no known activations.