© 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. 7137
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    ders
    -0.26
    åŃĺ
    -0.25
    metic
    -0.25
    getti
    -0.25
    ularity
    -0.24
     dam
    -0.24
    umerator
    -0.24
    uali
    -0.23
     Nug
    -0.23
     Nest
    -0.23
    POSITIVE LOGITS
    .bpm
    0.26
    bpp
    0.25
    /API
    0.25
    ä¸ĭæĿ¥
    0.25
     inexp
    0.23
    uv
    0.23
    ])]
    0.23
    irmingham
    0.23
     Fires
    0.23
    è¿Ľé©»
    0.23
    Activations Density 0.857%

    No Known Activations