© 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. 8524
    Prev
    Next
    INDEX
    Explanations

    verify

    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
    amat
    -0.25
     pains
    -0.23
    addComponent
    -0.23
    agos
    -0.23
    esson
    -0.23
    è¦ģ好好
    -0.22
    aises
    -0.21
    _handlers
    -0.21
     sposób
    -0.21
    POSITIVE LOGITS
    æĿ¡ä¾ĭ
    0.25
    ظ
    0.23
    ÃŃst
    0.23
     tal
    0.23
    马æĭī
    0.23
    主任
    0.23
    atively
    0.23
     Schro
    0.23
    utive
    0.22
    ked
    0.22
    Activations Density 2.118%

    No Known Activations