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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41258
    Prev
    Next
    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incomes
    -0.30
     piece
    -0.29
     Piece
    -0.29
    bil
    -0.28
    æ¸Ĭ
    -0.28
    åĪĹ
    -0.28
    å¤ĸè¯Ń
    -0.27
    piece
    -0.26
    GetX
    -0.26
    .piece
    -0.25
    POSITIVE LOGITS
    банк
    0.27
    chrom
    0.25
     ÑĢеÑĪа
    0.25
    åij¨ä¸Ģ
    0.24
    ÑĢом
    0.24
    ulares
    0.24
    çĽĽå¤§
    0.24
    .FindControl
    0.24
    çļĦçݰ象
    0.24
    odia
    0.23
    Activations Density 0.234%

    No Known Activations