© 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. 5954
    Prev
    Next
    INDEX
    Explanations

    Comparisons or differences

    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
    ingu
    -0.27
    Enumerable
    -0.26
     [|
    -0.26
    ä¸ĭ乡
    -0.25
    strained
    -0.25
    ä¹Łéĥ½
    -0.24
    hea
    -0.24
    onium
    -0.24
    åı¯è¡ĮæĢ§
    -0.23
    ¼
    -0.23
    POSITIVE LOGITS
    mun
    0.25
    yers
    0.25
    幡
    0.24
     tá»ĩ
    0.24
    heet
    0.24
     arrived
    0.24
     way
    0.24
    ("%.
    0.24
    ategory
    0.24
    OMP
    0.23
    Activations Density 0.013%

    No Known Activations