© 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. 107206
    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
    ãĥ¯ãĥ¼ãĤ¯
    -0.28
    osite
    -0.26
    uges
    -0.26
     nextPage
    -0.25
    人们çļĦ
    -0.24
    .Events
    -0.24
     Lot
    -0.24
    è°Ķ
    -0.24
     Fou
    -0.24
    趣
    -0.23
    POSITIVE LOGITS
    notated
    0.30
    éĻIJ
    0.28
     Shake
    0.24
    åĮĸçŁ³
    0.24
    aris
    0.24
    Girls
    0.24
    纪å½ķ
    0.23
    éĻIJå®ļ
    0.23
     recordings
    0.23
    hip
    0.23
    Activations Density 4.284%

    No Known Activations

    This feature has no known activations.