© 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. 63346
    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
    产åIJİ
    -0.28
    evt
    -0.27
    Inspectable
    -0.25
    enburg
    -0.25
    ays
    -0.24
    ç»Īæŀģ
    -0.24
    åIJĦé¡¹å·¥ä½ľ
    -0.24
    议论
    -0.24
    Posting
    -0.24
     boobs
    -0.23
    POSITIVE LOGITS
    çĻ¾
    0.27
    isoft
    0.27
    indle
    0.27
    ystore
    0.25
    çݯ
    0.24
     Concent
    0.24
    å½¢å¼ı
    0.24
    å®ŀè´¨
    0.23
    оÑī
    0.23
     Rare
    0.23
    Activations Density 18.444%

    No Known Activations

    This feature has no known activations.