© 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. 141864
    Prev
    Next
    INDEX
    Explanations

    cystic fibrosis

    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
     bond
    -0.27
    lie
    -0.27
    rou
    -0.26
    ä½³
    -0.26
     Nack
    -0.26
    arrant
    -0.25
    asking
    -0.25
    lien
    -0.25
    queries
    -0.25
    oire
    -0.24
    POSITIVE LOGITS
    cem
    0.32
    ç¾¼
    0.26
    .addField
    0.25
    éĥ¾
    0.25
    lename
    0.24
    cmc
    0.24
    åijĽ
    0.24
     iam
    0.24
    icorn
    0.24
    typeorm
    0.24
    Activations Density 5.539%

    No Known Activations