© 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. 150000
    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
     ump
    -0.27
    IFO
    -0.26
    è¦ģ害
    -0.24
     communic
    -0.24
    phoon
    -0.24
    itary
    -0.24
    ä¸Ģç«Ļå¼ı
    -0.24
     wrest
    -0.23
    umbo
    -0.23
    usty
    -0.23
    POSITIVE LOGITS
    课
    0.27
    課
    0.26
    SV
    0.24
    é¡ĺ
    0.23
     Ble
    0.23
    åIJĪãĤı
    0.23
    'al
    0.23
    (||
    0.23
    Systems
    0.23
    æ±Łèĭı
    0.23
    Activations Density 0.137%

    No Known Activations

    This feature has no known activations.