© 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. 8567
    Prev
    Next
    INDEX
    Explanations

    Numbers and percentages

    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
    antz
    -0.30
     Rosenstein
    -0.26
     depending
    -0.25
    çĶ¾
    -0.25
    ctic
    -0.24
    ivent
    -0.24
     satisfying
    -0.24
     potentials
    -0.24
     Franken
    -0.23
     potential
    -0.23
    POSITIVE LOGITS
    ero
    0.29
    anders
    0.28
    RODUCTION
    0.27
    oons
    0.26
    åĪĨå¸ĥ
    0.26
    eres
    0.26
    eros
    0.26
    åijĬ
    0.25
    åıªåī©
    0.25
    寸
    0.24
    Activations Density 0.816%

    No Known Activations