© 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. 63249
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    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
    obot
    -0.28
    æĭĴ
    -0.27
    éŃĶçİĭ
    -0.26
     Open
    -0.25
    ether
    -0.25
    éĵ£
    -0.25
     pert
    -0.24
    æĥ¯
    -0.24
    Open
    -0.24
    pert
    -0.24
    POSITIVE LOGITS
    åĽ½ç±į
    0.29
    æłĩçļĦ
    0.27
    å¾Ń
    0.26
    PubMed
    0.26
    arez
    0.25
    amous
    0.24
     Directorate
    0.24
    丰
    0.24
    olders
    0.23
     PubMed
    0.23
    Activations Density 17.779%

    No Known Activations