© 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. 141565
    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
    é³ı
    -0.28
    æµĨ
    -0.28
    Nonnull
    -0.25
    MASK
    -0.25
    nofollow
    -0.25
    ony
    -0.25
    mask
    -0.24
    splash
    -0.24
    ATING
    -0.24
    岿
    -0.24
    POSITIVE LOGITS
    çĶ¨å¿ĥ
    0.28
    æĬĬå®ĥ
    0.28
    çĶ¨åĬĽ
    0.28
     properly
    0.26
     Favor
    0.26
    Ñģоб
    0.26
     cruz
    0.25
    宣
    0.25
    ×Ļ×ķת
    0.24
    åĬ³
    0.24
    Activations Density 1.334%

    No Known Activations

    This feature has no known activations.