© 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. 142053
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
    iga
    -0.26
    åį´
    -0.25
     hes
    -0.25
    .setParameter
    -0.24
    ousel
    -0.24
    ìn
    -0.24
    itre
    -0.23
    Principal
    -0.23
    åį»
    -0.23
    æ´ŀ
    -0.23
    POSITIVE LOGITS
    ä¸įå¼Ģ
    0.35
    ä¸įéĢļ
    0.29
    éĥ½è®¤ä¸º
    0.27
    ä¸İæŶ
    0.26
    remen
    0.26
    æĿ¥ä¸įåıĬ
    0.26
    ä¸įèµ·
    0.25
    ä¸įåĨį
    0.25
    pek
    0.25
    Agents
    0.25
    Activations Density 18.076%

    No Known Activations