© 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. 130506
    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
     brows
    -0.28
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.26
    éĢĬ
    -0.26
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.25
    OLD
    -0.25
     OLD
    -0.25
    ãĤį
    -0.25
     acquaint
    -0.24
    sel
    -0.24
    č↵č↵č↵č↵
    -0.24
    POSITIVE LOGITS
     sinking
    0.26
     Kov
    0.25
     unfairly
    0.25
    èģªæĺİ
    0.24
    èµ·
    0.23
    èµ°å»Ĭ
    0.23
    oused
    0.23
    adin
    0.23
     Bip
    0.22
    帮åĬ©ä¼ģä¸ļ
    0.22
    Activations Density 0.240%

    No Known Activations

    This feature has no known activations.