© 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. 33-TRANSCODER-HP
    7. 53882
    Prev
    Next
    INDEX
    Explanations

    total

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wal
    -0.31
     frameworks
    -0.27
    é¡¿
    -0.26
    éħ¹
    -0.26
    wä
    -0.24
    æ¡Ĩ
    -0.24
    .JOptionPane
    -0.24
    LOS
    -0.24
    зон
    -0.23
    顾
    -0.23
    POSITIVE LOGITS
     total
    0.38
     Total
    0.35
    æĢ»
    0.33
    >Total
    0.32
    Total
    0.32
    	total
    0.29
    _total
    0.29
    total
    0.29
     TOTAL
    0.28
    TOTAL
    0.28
    Activations Density 0.008%

    No Known Activations