© 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. 20-TRANSCODER-HP
    7. 108210
    Prev
    Next
    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugas
    -0.29
    èݲ
    -0.26
    éĻ¢
    -0.25
    请åıĬæŶ
    -0.25
    icles
    -0.24
    ç¼ħ
    -0.24
    æŀģ端
    -0.24
    æ°´åĪĨ
    -0.24
    ä¸Ńå°ıåŀĭ
    -0.24
    èĢģ
    -0.24
    POSITIVE LOGITS
     turnaround
    0.27
    eeper
    0.27
    _IV
    0.26
    åĨ²åĬ¨
    0.25
     CultureInfo
    0.25
    ventions
    0.24
    .Ver
    0.24
    bö
    0.24
    |#
    0.24
     мил
    0.24
    Activations Density 15.405%

    No Known Activations