© 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. 5879
    Prev
    Next
    INDEX
    Explanations

    Civil War, World War

    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
    pn
    -0.26
    妾
    -0.24
     anon
    -0.24
     BÃł
    -0.24
     reform
    -0.24
    illos
    -0.24
     individual
    -0.23
     eigen
    -0.23
    _scripts
    -0.23
    castle
    -0.23
    POSITIVE LOGITS
    太ä¹ħ
    0.25
    çļĦä¸ĢéĿ¢
    0.25
    åı¦ä¸Ģè¾¹
    0.25
    å¤ļä¹ħ
    0.24
    emode
    0.24
    ä½łçļĦ
    0.24
    â»
    0.23
    avit
    0.23
    UIL
    0.23
    (pc
    0.23
    Activations Density 0.003%

    No Known Activations