© 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. 18988
    Prev
    Next
    INDEX
    Explanations

    Canada place names

    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
    èĴĻ
    -0.39
    Albert
    -0.30
     Prince
    -0.30
     Nuevo
    -0.27
     New
    -0.27
     masses
    -0.26
    Prince
    -0.26
    New
    -0.26
    odu
    -0.26
    æĸ°
    -0.25
    POSITIVE LOGITS
    EXPORT
    0.31
     Fa
    0.26
    ês
    0.26
    è·¡
    0.26
    Statement
    0.26
    Ni
    0.25
    .har
    0.24
     Statement
    0.24
     Geme
    0.24
     Counties
    0.24
    Activations Density 31.020%

    No Known Activations