© 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. 7322
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
    åħķ
    -0.27
    hy
    -0.26
     unint
    -0.25
     lxml
    -0.24
    awei
    -0.24
    åŀĭä¼ģä¸ļ
    -0.24
     Kapoor
    -0.23
     Wy
    -0.23
     hy
    -0.23
    erten
    -0.23
    POSITIVE LOGITS
     bordered
    0.27
     become
    0.26
     ground
    0.25
    ÇĶ
    0.25
    ips
    0.25
    beg
    0.24
     tolerant
    0.24
    mons
    0.24
    éĻį
    0.24
     entertain
    0.24
    Activations Density 0.016%

    No Known Activations