© 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. 108218
    Prev
    Next
    INDEX
    Explanations

    in

    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
    -thumb
    -0.26
     landlords
    -0.25
     <![
    -0.25
    uls
    -0.24
    disposing
    -0.24
     indispensable
    -0.24
     republic
    -0.23
    olis
    -0.23
    RE
    -0.23
    quo
    -0.23
    POSITIVE LOGITS
    èĴĮ
    0.28
    .getBean
    0.27
    èµ°ä¸ĭåİ»
    0.26
    æ´
    0.26
    onder
    0.25
    angel
    0.25
     getVersion
    0.25
    ynn
    0.24
    èĢĮ导èĩ´
    0.24
    éĢł
    0.24
    Activations Density 4.975%

    No Known Activations