© 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. 142299
    Prev
    Next
    INDEX
    Explanations

    Scientific publications

    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
    ç»į
    -0.28
    ulling
    -0.27
    ayne
    -0.26
    -txt
    -0.26
     Vs
    -0.25
    ancode
    -0.25
    opic
    -0.25
    fluence
    -0.25
    resents
    -0.25
    _ty
    -0.25
    POSITIVE LOGITS
    ''
    0.27
    ç»ıåķĨ
    0.25
    å³»
    0.25
    LOCITY
    0.24
     licensed
    0.24
    à¸Ħม
    0.24
    ноп
    0.24
    èħº
    0.23
    IÃĵN
    0.23
    .spi
    0.23
    Activations Density 0.187%

    No Known Activations