© 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. 108354
    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
    __/
    -0.25
    å±±åĮº
    -0.24
    USR
    -0.24
    callbacks
    -0.24
    æĻ®éģį
    -0.23
    éĩįå·¥
    -0.23
     Meadows
    -0.23
    å¿Ĺ强
    -0.23
    -derived
    -0.23
    循
    -0.23
    POSITIVE LOGITS
    马ä¸ģ
    0.28
     Stein
    0.28
    æ¿¡
    0.27
    é»
    0.25
     pregn
    0.25
    pring
    0.25
     Rand
    0.25
    Rand
    0.25
    ogram
    0.25
     radiator
    0.25
    Activations Density 14.062%

    No Known Activations

    This feature has no known activations.