© 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. 5919
    Prev
    Next
    INDEX
    Explanations

    also

    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
    åĤ¢
    -0.27
    CRT
    -0.27
     Caval
    -0.27
    LOT
    -0.27
    æłĩ
    -0.26
    æĭĽ
    -0.25
    æĭīçĿĢ
    -0.25
    raj
    -0.25
    lot
    -0.25
    king
    -0.25
    POSITIVE LOGITS
    facet
    0.26
    ä¸Ģ审
    0.24
    ãĢij↵↵
    0.24
    鸾
    0.23
    äs
    0.23
    ensch
    0.23
    hsi
    0.23
     ffi
    0.23
    fte
    0.23
    heed
    0.23
    Activations Density 0.001%

    No Known Activations