© 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. 107743
    Prev
    Next
    INDEX
    Explanations

    period

    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
    eur
    -0.32
     nor
    -0.31
    nor
    -0.30
     middle
    -0.28
    ä¹Łä¸į
    -0.27
    ellar
    -0.27
    ä¹Łæ²¡æľī
    -0.26
    Former
    -0.25
    海峡
    -0.25
    eller
    -0.25
    POSITIVE LOGITS
    好äºĨ
    0.26
    ä¸ĩåħĥ以ä¸Ĭ
    0.25
     Gad
    0.25
    大家åĪĨ享
    0.25
    eterangan
    0.24
    idges
    0.24
     "...
    0.24
     stdout
    0.24
     backgroundImage
    0.24
    åѦåĪ°
    0.24
    Activations Density 18.508%

    No Known Activations