© 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. 141950
    Prev
    Next
    INDEX
    Explanations

    Generic English text

    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
    Ợ
    -0.28
    owns
    -0.27
    çı¥
    -0.25
    ockets
    -0.25
     Bip
    -0.25
    两ä½į
    -0.24
    社ä¼ļåĮĸ
    -0.24
    ä¸Ģ项
    -0.24
    öz
    -0.24
    _MR
    -0.24
    POSITIVE LOGITS
    æŶåĪ»
    0.29
    年纪
    0.27
    â»
    0.26
    åĽĽåŃ£
    0.26
     seasons
    0.26
    /latest
    0.25
    è¿ĩ
    0.25
    é¾Ħ
    0.25
     ages
    0.25
    ptime
    0.25
    Activations Density 54.104%

    No Known Activations