© 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. 8000
    Prev
    Next
    INDEX
    Explanations

    Official documents and court cases

    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
    aget
    -0.29
    èĤ¢
    -0.27
    lda
    -0.27
    åģļä¸ĢäºĽ
    -0.25
    ee
    -0.25
    grounds
    -0.25
    _LCD
    -0.24
    å²ģ以ä¸Ĭ
    -0.24
    UDA
    -0.24
    obby
    -0.23
    POSITIVE LOGITS
    present
    0.29
     presente
    0.28
    PRESENT
    0.27
     Present
    0.27
    大å°ı
    0.26
     present
    0.26
    Present
    0.26
    宿
    0.25
    présent
    0.24
    çŃ¾åŃĹ
    0.23
    Activations Density 0.004%

    No Known Activations