© 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. 5409
    Prev
    Next
    INDEX
    Explanations

    Country names/parts

    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
    æ¾ľ
    -0.27
     inspection
    -0.26
    ÑģÑĤи
    -0.25
    ¹
    -0.25
    æĭĴ
    -0.25
    缸åıį
    -0.24
    adi
    -0.24
    rog
    -0.24
    -0.24
    :
    -0.24
    POSITIVE LOGITS
    ood
    0.26
    ä¸Ģ棵
    0.26
    .modelo
    0.25
    çļĦ形象
    0.25
     bingo
    0.24
    (sq
    0.24
    Credits
    0.24
     Luxury
    0.24
     dictatorship
    0.23
    ourage
    0.23
    Activations Density 0.933%

    No Known Activations