© 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. 141536
    Prev
    Next
    INDEX
    Explanations

    Common English words

    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
    logue
    -0.28
    éĿ©æĸ°
    -0.26
     Lip
    -0.25
     Drain
    -0.24
    æĺİæĻº
    -0.24
    é²£
    -0.24
    大大å°ıå°ı
    -0.24
    QtCore
    -0.24
    lip
    -0.24
    åĨħå¤ĸ
    -0.23
    POSITIVE LOGITS
    alled
    0.26
    æĬĺ
    0.26
    交
    0.25
    æ°Ķ
    0.24
     подпиÑģ
    0.24
    ZZ
    0.24
     arms
    0.24
    ocado
    0.24
    åĩĨ
    0.24
    å¾Ĺèµ·
    0.24
    Activations Density 60.406%

    No Known Activations