© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7279
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    æį
    -0.27
    ableObject
    -0.26
    UnityEngine
    -0.26
    unct
    -0.25
    .getElement
    -0.25
     UObject
    -0.25
    (console
    -0.25
    unge
    -0.25
    olio
    -0.24
    oons
    -0.24
    POSITIVE LOGITS
    ä¸īå±Ĥ
    0.30
    ä¸ľè¥¿
    0.27
    k
    0.26
    ter
    0.26
    ewith
    0.25
     k
    0.24
    æķħæĦı
    0.24
     trading
    0.24
    elsif
    0.23
    è¿ĩæķı
    0.23
    Activations Density 0.009%

    No Known Activations