© 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. 7374
    Prev
    Next
    INDEX
    Explanations

    Types of people

    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
    .hstack
    -0.26
    pleted
    -0.26
    _FLUSH
    -0.26
    throp
    -0.26
     accordingly
    -0.25
     opposite
    -0.25
    ernes
    -0.25
    èį¡
    -0.25
    lds
    -0.24
    oscope
    -0.24
    POSITIVE LOGITS
    ç²Ĺ
    0.28
     getopt
    0.25
     conform
    0.25
    _TER
    0.24
     ÙĦبÙĨاÙĨ
    0.24
     *))
    0.24
    con
    0.24
    绿
    0.23
    ubic
    0.23
    ç»ı常
    0.23
    Activations Density 0.095%

    No Known Activations