© 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. 63691
    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
     tav
    -0.29
    ëŀĢ
    -0.27
    ancy
    -0.26
    ãĥĥãĤ·ãĥ¥
    -0.25
     tuned
    -0.25
     createAction
    -0.24
    ãĥģãĥ¥
    -0.24
    -cloud
    -0.24
    .getAs
    -0.24
     processo
    -0.23
    POSITIVE LOGITS
    arend
    0.30
    å¹³åĿĩæ¯ı
    0.28
    ĵį
    0.27
    \\/
    0.26
     Canonical
    0.26
    æĶ¿
    0.24
     canonical
    0.24
    èģĶåĬ¨
    0.24
     Canon
    0.23
    patterns
    0.23
    Activations Density 0.166%

    No Known Activations

    This feature has no known activations.