© 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. 130262
    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
     Mondays
    -0.30
     pencils
    -0.28
     relu
    -0.28
    VILLE
    -0.26
    ä»ĬçĶŁ
    -0.25
    _emails
    -0.25
     postpone
    -0.24
    ଡ
    -0.24
    é«Ń
    -0.24
    wik
    -0.24
    POSITIVE LOGITS
    amiliar
    0.29
    ç½ķ
    0.27
    ont
    0.26
    éĤ£äºº
    0.26
    onto
    0.26
    orce
    0.26
    cum
    0.26
     youre
    0.25
     Classifier
    0.25
     Kore
    0.24
    Activations Density 3.410%

    No Known Activations

    This feature has no known activations.