© 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. 39927
    Prev
    Next
    INDEX
    Explanations

    Borneo

    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
    æĪIJåijĺ
    -0.29
    itionally
    -0.29
    composition
    -0.27
    åħĪè¿Ľ
    -0.26
    fern
    -0.26
     Composition
    -0.25
    身份
    -0.25
    .vaadin
    -0.24
    FXML
    -0.24
     ferment
    -0.24
    POSITIVE LOGITS
    梳
    0.26
     semi
    0.25
     aux
    0.24
    éļĨ
    0.24
     ros
    0.24
    UD
    0.24
    intel
    0.24
    äºĨ个
    0.24
    åįĬ
    0.24
    åĪ©äºİ
    0.24
    Activations Density 1.145%

    No Known Activations