© 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. 141518
    Prev
    Next
    INDEX
    Explanations

    defects

    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
    æĸĩåŃĹ
    -0.28
    ĮĢ
    -0.27
    å¥Ĺ
    -0.25
    (option
    -0.25
    ä»ĸå°±
    -0.24
    ä¹ħ
    -0.24
    keywords
    -0.24
    æľįåĬ¡åĮº
    -0.23
     equivalents
    -0.23
     Him
    -0.23
    POSITIVE LOGITS
    å¤įå·¥
    0.27
    们éĥ½
    0.26
    apus
    0.24
    å¤įå·¥å¤į产
    0.24
    ä¸Ŀä¸Ŀ
    0.23
    æīįå¹²
    0.23
    代çIJĨ
    0.23
    hape
    0.23
    s
    0.23
    /arch
    0.23
    Activations Density 7.580%

    No Known Activations