© 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. 141304
    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
    éĴ´
    -0.29
    otor
    -0.25
     ÐŀÐŀÐŀ
    -0.25
    zeug
    -0.25
    راض
    -0.24
    ovsky
    -0.24
    _PAYLOAD
    -0.24
    åĮ»
    -0.24
    |=↵
    -0.23
    acky
    -0.23
    POSITIVE LOGITS
    æ¶ķ
    0.35
    æľīä¸Ģä½į
    0.28
    ABL
    0.26
    _aliases
    0.25
    intel
    0.24
    _alias
    0.24
    åĽłä¸ºæĪij
    0.23
    /Main
    0.23
    ç«ŀèµĽ
    0.23
     tess
    0.23
    Activations Density 4.412%

    No Known Activations

    This feature has no known activations.