© 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. 64342
    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
    以为
    -0.26
    åĪ°äºĨ
    -0.26
    æ³
    -0.25
     domaine
    -0.25
    çģŃçģ«
    -0.25
    çļĩåIJİ
    -0.25
    ä¼Łå¤§çļĦ
    -0.25
    ustr
    -0.25
    walker
    -0.24
     stuff
    -0.23
    POSITIVE LOGITS
    eware
    0.25
     setSelected
    0.25
     Slut
    0.24
    наÑĤ
    0.24
    {l
    0.24
    ése
    0.23
    è¿Ļç±»
    0.23
     bi
    0.23
    )b
    0.23
    éľ²
    0.22
    Activations Density 54.840%

    No Known Activations

    This feature has no known activations.