© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5876
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    rogen
    -0.27
    quil
    -0.25
    ernal
    -0.25
     entire
    -0.24
     Course
    -0.24
    erland
    -0.23
    aurus
    -0.23
    -Dec
    -0.23
     Ãĥ
    -0.23
    icle
    -0.23
    POSITIVE LOGITS
    idy
    0.28
     hung
    0.27
    å¤Ħ
    0.25
    ظÙĩ
    0.25
    tru
    0.24
    uraa
    0.24
    æĮĤ
    0.24
     toe
    0.24
    建
    0.24
    ç´ł
    0.24
    Activations Density 1.072%

    No Known Activations