© 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. 141923
    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
    emia
    -0.25
    uition
    -0.25
    丢äºĨ
    -0.24
    ismo
    -0.24
    uid
    -0.23
    Imp
    -0.23
    iete
    -0.23
    Capability
    -0.23
    Shock
    -0.23
     Kenya
    -0.23
    POSITIVE LOGITS
    çijķ
    0.29
    retched
    0.28
    è¾Ľ
    0.28
    ä½Ļ
    0.26
     excludes
    0.25
    çī¹åĪ«å£°æĺİ
    0.25
     exaggerated
    0.25
     stretch
    0.25
    æī§
    0.24
    空
    0.24
    Activations Density 5.225%

    No Known Activations

    This feature has no known activations.