© 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. 19-TRANSCODER-HP
    7. 7719
    Prev
    Next
    INDEX
    Explanations

    external

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erot
    -0.25
     Graf
    -0.25
    AdminController
    -0.24
    CEE
    -0.24
    erman
    -0.24
     currentItem
    -0.23
     haircut
    -0.23
    idis
    -0.23
     Versions
    -0.23
    å§ĭ建
    -0.23
    POSITIVE LOGITS
     rather
    0.26
    èĢĮéĿŀ
    0.24
    eldorf
    0.24
    orthy
    0.24
    äºĶä¸Ģ
    0.24
    ally
    0.23
    ìĬ¤íĬ¸
    0.23
    çį¨ç«ĭ
    0.23
    æĽ´å¤ļ精彩
    0.23
    OUS
    0.23
    Activations Density 0.154%

    No Known Activations