© 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. 27-TRANSCODER-HP
    7. 8320
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    举
    -0.32
     parted
    -0.28
     Rounded
    -0.27
     Reds
    -0.27
     paused
    -0.27
    peror
    -0.27
    ãĤ·ãĥ¼ãĤºãĥ³
    -0.26
    åij¨äºĶ
    -0.26
    idend
    -0.26
    -rounded
    -0.26
    POSITIVE LOGITS
     present
    0.29
    odos
    0.29
    转åIJij
    0.28
    æļ
    0.28
     introdu
    0.28
     Ãł
    0.28
    ihu
    0.28
    空çĻ½
    0.28
    çĿĢæīĭ
    0.28
    érie
    0.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.