© 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. 107019
    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
    azor
    -0.26
    bout
    -0.25
    åħĭåĪ¶
    -0.25
     PLEASE
    -0.24
    asco
    -0.24
    æŃ¢
    -0.24
    ç»ĨèĬĤ
    -0.24
     fuera
    -0.24
     stripped
    -0.23
    kowski
    -0.23
    POSITIVE LOGITS
    FromArray
    0.28
    çļĦæłĩåĩĨ
    0.28
     lids
    0.26
    regar
    0.25
     wakes
    0.24
    骥
    0.24
     initializes
    0.24
     Initializes
    0.24
    éĻŁ
    0.24
    èĭķ
    0.24
    Activations Density 12.696%

    No Known Activations

    This feature has no known activations.