© 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. 14-TRANSCODER-HP
    7. 40022
    Prev
    Next
    INDEX
    Explanations

    technical/code-related content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼Ĥåij³
    -0.29
     tainted
    -0.29
    æĦŁ
    -0.28
     contaminated
    -0.28
    çī©åĵģ
    -0.27
    个人信æģ¯
    -0.27
     humid
    -0.27
    çĨı
    -0.27
     inhal
    -0.27
    uario
    -0.27
    POSITIVE LOGITS
    serve
    0.27
    å½¢å¼ı
    0.26
    segments
    0.25
    åĪĩãĤĮ
    0.25
    collector
    0.24
    DDL
    0.24
    rac
    0.24
     sliced
    0.24
    è·¨
    0.24
    sek
    0.24
    Activations Density 2.112%

    No Known Activations