© 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. 142223
    Prev
    Next
    INDEX
    Explanations

    Technical or academic documents

    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
    _estimator
    -0.28
    估计
    -0.27
    redd
    -0.26
    .invoke
    -0.25
    åĮĸè¿Ľç¨ĭ
    -0.24
    åįłçĶ¨
    -0.23
     sez
    -0.23
    elif
    -0.23
     MPG
    -0.23
    åıªè§ģ
    -0.23
    POSITIVE LOGITS
    aniu
    0.27
    lessly
    0.26
    ìĦ±ìĿĦ
    0.25
    -CN
    0.25
    åĴĮåıijå±ķ
    0.25
    leon
    0.24
     optimization
    0.24
    èįĶ
    0.24
    ابت
    0.24
     ath
    0.23
    Activations Density 1.232%

    No Known Activations