© 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. 9126
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ä½ĵåĨħ
    -0.27
    embr
    -0.26
    tbody
    -0.26
    .Our
    -0.26
    -react
    -0.24
    resentation
    -0.24
    isans
    -0.24
    åħ¥ãĤĬ
    -0.24
    renders
    -0.23
    翼
    -0.23
    POSITIVE LOGITS
     Lock
    0.27
     pop
    0.26
     either
    0.26
     Field
    0.26
    åħ¬å¼Ģ
    0.25
    |
    0.25
    Âł
    0.25
    âĢ
    0.25
    uggy
    0.25
    é¦Ļ
    0.25
    Activations Density 0.026%

    No Known Activations