© 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. 142359
    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
     rig
    -0.27
    ÑĢаг
    -0.27
    Struct
    -0.27
     rog
    -0.26
    Ware
    -0.26
    \a
    -0.26
    åĭĺ
    -0.25
    转载请
    -0.25
    ika
    -0.24
    earn
    -0.24
    POSITIVE LOGITS
    enth
    0.32
     alone
    0.29
    pared
    0.28
    åŁºæķ°
    0.28
    -alone
    0.27
    çį¨
    0.26
    çĭ¬
    0.26
     Alone
    0.26
    æŃ¥æŃ¥
    0.26
     breathable
    0.25
    Activations Density 14.954%

    No Known Activations

    This feature has no known activations.