© 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. 31-TRANSCODER-HP
    7. 19177
    Prev
    Next
    INDEX
    Explanations

    Code and technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĤį
    -0.29
     Esp
    -0.26
    ronic
    -0.26
    å°Ĭ严
    -0.26
     inf
    -0.26
    developers
    -0.25
    绣ä¸Ģ
    -0.25
     dignity
    -0.25
    è°
    -0.25
    èµ°åIJij
    -0.25
    POSITIVE LOGITS
    <Group
    0.30
    (Group
    0.27
     group
    0.27
    ä½ı宿
    0.26
    illage
    0.25
    .ra
    0.25
    æĿµ
    0.24
     kir
    0.24
    æİı
    0.24
    \"></
    0.24
    Activations Density 1.411%

    No Known Activations