© 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. 5802
    Prev
    Next
    INDEX
    Explanations

    one

    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
     -:
    -0.28
     Chance
    -0.27
     CAPITAL
    -0.24
    /apt
    -0.24
    gren
    -0.24
    capital
    -0.24
     chance
    -0.23
     gÃł
    -0.23
    rypto
    -0.23
    人们çļĦ
    -0.23
    POSITIVE LOGITS
    ç»Ļä»ĸ们
    0.27
     commenter
    0.26
    让ä»ĸ们
    0.25
     apprent
    0.25
    å¼¹
    0.24
     transitioning
    0.24
    .Navigator
    0.24
    лом
    0.24
    åĵij
    0.24
    çªį
    0.24
    Activations Density 0.027%

    No Known Activations