© 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. 30-TRANSCODER-HP
    7. 96004
    Prev
    Next
    INDEX
    Explanations

    countries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vietnamese
    -0.78
     Brazilian
    -0.76
     Japanese
    -0.75
     Indonesian
    -0.75
     Australian
    -0.75
     Chinese
    -0.74
     Taiwanese
    -0.74
     Romanian
    -0.71
    Japanese
    -0.71
     Canadian
    -0.70
    POSITIVE LOGITS
     America
    0.44
     France
    0.44
     Italy
    0.41
     Arabia
    0.41
     Russia
    0.40
     Ireland
    0.40
     Canada
    0.40
    America
    0.40
     Greece
    0.40
     Sweden
    0.40
    Activations Density 1.056%

    No Known Activations