© 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. 130447
    Prev
    Next
    INDEX
    Explanations

    articles and possessives

    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
     specs
    -0.27
     Specs
    -0.25
     hairs
    -0.25
    ester
    -0.25
    鸡
    -0.25
    estival
    -0.24
    esk
    -0.24
    ç¯Ļ
    -0.24
    ning
    -0.23
    akers
    -0.23
    POSITIVE LOGITS
    ä¸įç»ı
    0.28
    icated
    0.27
     Atl
    0.26
    èĩ¼
    0.26
    anders
    0.25
    认è¯ĨåĪ°
    0.25
    otron
    0.25
    aho
    0.25
    (blob
    0.24
     Texans
    0.24
    Activations Density 30.359%

    No Known Activations