© 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. 41370
    Prev
    Next
    INDEX
    Explanations

    cases and France

    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
    åħ¨æĹ¥
    -0.25
    é¢ĩ为
    -0.24
    主é¢ĺ
    -0.24
     colossal
    -0.23
    zell
    -0.23
    为主é¢ĺçļĦ
    -0.23
     continental
    -0.23
    é¢ĩ
    -0.23
     discipline
    -0.23
     catastrophic
    -0.23
    POSITIVE LOGITS
    oque
    0.30
    bane
    0.29
    viously
    0.28
    âŦ
    0.27
    使èĢħ
    0.27
    æıIJ
    0.26
    usan
    0.26
    arine
    0.26
    yne
    0.26
    ç¾½
    0.26
    Activations Density 1.140%

    No Known Activations