© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 139
    Prev
    Next
    INDEX
    Explanations

    research or PowerShell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ñģебе
    -0.27
    人åĿĩ
    -0.27
     spine
    -0.26
    ä¸įæľį
    -0.26
    ä¸įçIJĨ
    -0.26
    æīįæĺ¯çľŁæŃ£
    -0.26
    ä¹Łå¸ĮæľĽ
    -0.25
    ä¹ŁéľĢè¦ģ
    -0.25
    æĺ¯ä½ł
    -0.25
    erge
    -0.25
    POSITIVE LOGITS
    æļĦ
    0.29
    azel
    0.27
    aro
    0.27
    енко
    0.26
     nor
    0.26
    åŃ£åIJİ
    0.25
    anka
    0.24
    agrid
    0.24
    iba
    0.24
    eln
    0.24
    Activations Density 0.046%

    No Known Activations