© 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. 130514
    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
     sprink
    -0.26
    .cg
    -0.24
     Fiesta
    -0.24
    ansa
    -0.24
    áºĵ
    -0.23
    æīĭç»Ń
    -0.23
    aylight
    -0.23
    [np
    -0.23
    ONTAL
    -0.23
    /&
    -0.23
    POSITIVE LOGITS
    èĬ±çĵ£
    0.28
     Exact
    0.27
    phinx
    0.27
    nameof
    0.26
    Exact
    0.25
    asts
    0.25
    TERS
    0.25
    chers
    0.25
    ters
    0.25
    .Framework
    0.25
    Activations Density 25.472%

    No Known Activations

    This feature has no known activations.