© 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. 24-TRANSCODER-HP
    7. 150290
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .dex
    -0.29
    çīĮ
    -0.28
    loh
    -0.25
    ä¼ļè°Ī
    -0.24
    awah
    -0.24
    emailer
    -0.23
    大èĦij
    -0.23
    arms
    -0.23
    /big
    -0.23
    ixer
    -0.23
    POSITIVE LOGITS
    ç³»ç»ŁçļĦ
    0.23
    eous
    0.23
    _NE
    0.23
    gere
    0.23
    åIJ¸å¼ķæĽ´å¤ļ
    0.23
    éľĩæĥĬ
    0.23
    éĻ¨
    0.23
    åıĭ好
    0.22
     consc
    0.22
    .Controller
    0.22
    Activations Density 3.610%

    No Known Activations

    This feature has no known activations.