© 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. 12-TRANSCODER-HP
    7. 23797
    Prev
    Next
    INDEX
    Explanations

    high-throughput

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĢĻ
    -0.32
    uggle
    -0.28
     Pret
    -0.25
    ä»»
    -0.25
    éĢļ
    -0.24
    é©·
    -0.24
    ä½¼
    -0.24
     appointment
    -0.23
     Appointment
    -0.23
    ä¸įåıĬ
    -0.23
    POSITIVE LOGITS
    åģļçļĦ
    0.29
    gener
    0.27
    UTF
    0.26
    åĴ¬
    0.26
    enumer
    0.25
     Eden
    0.25
     nil
    0.25
    ä¸Ģç»ı
    0.24
    chip
    0.24
    hil
    0.24
    Activations Density 0.002%

    No Known Activations